system

Abstract

We provide the system. [Solution] A means by which the user inputs the target and performance data to be evaluated, A means for the terminal to send the entered data to the server, The means by which the server receives and stores data, A means by which the server activates a generative AI based on the stored data and starts the analysis process, A means by which a generative AI analyzes data and generates a score based on evaluation criteria, A means for saving the evaluation results generated by the server, A means by which the terminal displays the evaluation results to the user, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional Management by Objectives (MBO) evaluations and grade core certifications, there are problems that the evaluation is strongly influenced by the subjectivity of the evaluator, so the evaluation lacks consistency and objectivity cannot be maintained. Also, since it takes a lot of labor and time, there is a problem that it is difficult to perform evaluations efficiently.

Means for Solving the Problems

[0005] The present invention provides a system that performs MBO evaluation and grade core certification using generative AI. The present invention is a system that includes means for a user to input objective and performance data to be evaluated, means for a terminal to transmit the input data to a server, means for the server to receive and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, and means for the terminal to display the evaluation results to the user.

[0006] This eliminates subjective opinions and enables objective and efficient evaluation. Furthermore, using pre-trained generative AI models improves the consistency and accuracy of evaluation criteria. Additionally, including mechanisms to check the completeness and integrity of data upon receipt enhances the reliability of the evaluation process.

[0007] A "user" is an individual or organization whose role is to access the system, input goals and performance data, and review the evaluation results.

[0008] A "terminal" refers to a device used by a user to input goals and performance data and communicate with a server. Specifically, this includes PCs, smartphones, and tablets.

[0009] A "server" is a computer system that receives and stores data sent from users and terminals, and also launches generative AI to execute evaluation processes.

[0010] "Generative AI" refers to artificial intelligence models that analyze input data and generate scores based on pre-set evaluation criteria.

[0011] "Evaluation target" refers to data related to the goals and performance that the user intends to evaluate.

[0012] "Target data" refers to specific information about the goals that users have set as the behaviors or results to be evaluated.

[0013] "Performance data" refers to specific information about the results of the achievements and activities actually accomplished by the person being evaluated.

[0014] A "database" is a storage device used by a server to store user input data and evaluation results generated by AI.

[0015] "Evaluation criteria" refer to the specific rules and parameters that serve as indicators when a generative AI analyzes input data and generates a score.

[0016] A "score" refers to a numerical value or evaluation result calculated by a generative AI based on evaluation criteria.

[0017] "Reliability" refers to the degree to which a system provides consistent evaluations and the accuracy of those evaluation results.

[0018] "Completeness" refers to a state in which data is processed without any omissions or errors from input to storage.

[0019] "Consistency" refers to a state where data is consistent and free from contradictions. [Brief explanation of the drawing]

[0020] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5]It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] To implement this invention, it is necessary to construct a system in which users, terminals, and servers collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0042] User-side actions

[0043] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input specific objectives such as "Project A's objective is a 15% increase in sales" or actual performance data such as "Q1 sales increased by 10%."

[0044] Terminal-side operation

[0045] The terminal's role is to send data entered by the user to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP request. Data transmission is protected using security protocols such as SSL / TLS.

[0046] Server-side operation

[0047] The server's role is to receive and store data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server launches a generative AI. This uses a machine learning model implemented in a programming language such as Python.

[0048] The generative AI analyzes the input target and performance data and generates scores based on pre-set evaluation criteria. For example, if the evaluation criteria for sales growth rate are trained to be "10% increase = 85 points," the AI ​​will generate scores accordingly. The server stores the generated scores in a database.

[0049] Displaying Results

[0050] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" will be displayed.

[0051] Specific example

[0052] For example, the following evaluation process is possible.

[0053] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0054] 2. The device sends this data to the server.

[0055] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0056] 4. The server activates the generative AI and analyzes the data.

[0057] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the server saves this evaluation score to the database.

[0058] 6. The server sends the evaluation score to the terminal.

[0059] 7. The device displays the evaluation score to the user.

[0060] Through the above process, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0061] The following describes the processing flow.

[0062] Step 1:

[0063] Users input the target goals and performance data to be evaluated into their terminal. Specifically, after logging in, users access the evaluation form and input data such as "Project A's goal is a 15% increase in sales" or "Q1 sales increased by 10%."

[0064] Step 2:

[0065] The terminal sends data entered by the user to the server. The terminal converts the data to an appropriate format and sends it to the server using an HTTP POST request or similar method. During this process, SSL / TLS is used to encrypt the data transmission.

[0066] Step 3:

[0067] The server receives data sent from the terminal. The server verifies the integrity and validity of the data and returns an error message to the terminal if there are any errors. If there are no problems, the server saves this data to the database.

[0068] Step 4:

[0069] The server launches a generative AI based on the stored data. Specifically, the server calls a machine learning model implemented in Python or another language and starts the evaluation process.

[0070] Step 5:

[0071] Generative AI analyzes data and generates a score based on evaluation criteria. For example, if the input is "sales growth rate of 10%", a pre-trained model will analyze this and generate a score of "85 points".

[0072] Step 6:

[0073] The server saves the generated evaluation results to a database. When saving, metadata such as the date and time the evaluation was performed and the evaluation criteria are also saved along with the score.

[0074] Step 7:

[0075] The server sends the evaluation results to the terminal. The server returns the evaluation results to the terminal as an HTTP response. The terminal receives this response.

[0076] Step 8:

[0077] The device displays the evaluation results to the user. Specifically, when the user accesses the dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" is displayed. Based on this information, the user can take further actions or make decisions.

[0078] Through these steps, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0079] (Example 1)

[0080] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0081] Existing evaluation systems often lack objectivity and consistency in their assessments, and subjectivity is particularly likely to creep into the analysis and scoring of evaluation data, making fair evaluation difficult. Furthermore, the evaluation process is often manual, resulting in high time and effort requirements and low efficiency. Additionally, insufficient verification of the integrity and completeness of input data can lead to inaccurate evaluation results.

[0082] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0083] In this invention, the server includes means for the user to input target and performance data to be evaluated, means for the terminal to transmit the input data to the server, means for the server to receive, verify, and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, means for the server to transmit the evaluation results to the terminal, and means for the terminal to display the evaluation results to the user. This ensures objectivity and consistency in evaluation and enables an efficient and accurate evaluation process.

[0084] A "user" refers to an individual or legal entity that is responsible for inputting goal and performance data using the evaluation system.

[0085] "Terminal" refers to a device (e.g., PC, smartphone) that a user uses to access the evaluation system and input and transmit data.

[0086] A "server" refers to a central processing unit that receives data sent from terminals and performs storage and analysis processes.

[0087] "Goal and performance data" refers to numerical or string data entered by the user that indicates specific goals subject to evaluation and their achievement status.

[0088] "Transmission" refers to the act of a terminal transferring data entered by the user to a server.

[0089] "Receiving" refers to the act of a server receiving data sent from a terminal.

[0090] "Verification" refers to the process of confirming the integrity and validity of the data received by the server.

[0091] "Saving" refers to the act of a server recording received data or generated evaluation results in a database.

[0092] "Generative AI" refers to artificial intelligence models trained to perform data analysis and generate evaluation scores.

[0093] The "analysis process" refers to a series of processes by which a generative AI analyzes data and generates a score based on evaluation criteria.

[0094] "Evaluation criteria" refers to pre-set standards used by generative AI when scoring data.

[0095] "Evaluation results" refer to the scores generated by a generative AI based on evaluation criteria after data analysis.

[0096] "Display" refers to the act of showing the evaluation results received by the terminal from the server on the screen in a format that the user can see.

[0097] This invention aims to improve the objectivity and efficiency of evaluations by constructing a system in which users, terminals, and servers collaborate to perform the evaluation process. In this system, users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0098] User-side actions

[0099] Users access the system's evaluation form using their own devices, such as PCs or smartphones. In the evaluation form, users are responsible for entering goal and performance data. For example, a user might enter goal data such as "Project A's goal is a 15% increase in sales" or performance data such as "Q1 sales increased by 10%." The data entered by users plays a crucial role in the system's evaluation process.

[0100] Terminal-side operation

[0101] The terminal's role is to send data entered by the user to the server. Once the user finishes entering data into the evaluation form, the terminal formats this data into an appropriate format (e.g., JSON or XML) and sends it to the server using an HTTP request. During this process, security protocols such as SSL / TLS are used to protect the data during transmission.

[0102] Server-side operation

[0103] The server is the central processing unit that receives data sent from terminals and performs storage and analysis processes. First, the server checks the integrity and consistency of the received data. This verification includes checking the data format and verifying required fields. Once verification is complete, the data is stored in the database. This is done using database operation commands such as SQL.

[0104] Once data is saved, the server launches a generative AI. This generative AI is implemented as a Python script and uses a machine learning model trained for specific data analysis and scoring. The server passes the saved data to the AI ​​model for analysis. The generative AI analyzes the received data and generates a score based on pre-defined evaluation criteria. For example, if the evaluation criterion for sales growth rate is set to "10% increase = 85 points," the AI ​​will calculate the score accordingly.

[0105] The evaluation score generated as a result of the analysis is saved again to the database. After the evaluation score is saved, the server sends the evaluation result to the terminal. The terminal receives this data and displays the evaluation result on the user's screen.

[0106] Specific example

[0107] For example, the following evaluation process is possible:

[0108] 1. The user opens a browser on their device and accesses a specific URL (e.g., https: / / example.com / evaluation). They then enter the following data into the displayed evaluation form: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0109] 2. When the device clicks the "Submit" button, the browser's JavaScript® code converts the form data into JSON format and sends a POST request to the server using the HTTPS protocol with SSL / TLS.

[0110] 3. The server receives the request and verifies the format and content of the received data. It checks for format errors and missing required fields.

[0111] 4. The server establishes a database connection and inserts the performance data into the appropriate table in the database using an SQL INSERT statement.

[0112] 5. Once data saving is complete, the server executes a Python script to load a machine learning model (e.g., scikit-learn or TENSORFLOW®). The saved database data is then passed to the model.

[0113] 6. The generating AI inputs data into the model and generates an evaluation score, such as "5% cost reduction = 70 points". The score is stored in temporary memory.

[0114] 7. The server receives the evaluation score and executes an SQL query such as "INSERT INTO scoretable (project, score) VALUES ('project B', 70);" to save the score to the database.

[0115] 8. After the save operation, the server creates an HTTP response containing the evaluation score on the terminal and sends the evaluation result in JSON format in the response body.

[0116] 9. The device receives the HTTP response and parses the JSON response body using JavaScript. The evaluation result is displayed in a UI component (e.g., the evaluation result section of the dashboard), visually informing the user that "Q1 sales growth rate evaluation: 70 points".

[0117] Examples of prompt statements are as follows:

[0118] "Project B's objective is a 10% cost reduction for the department, and the actual result was a 5% cost reduction in Q1. Please generate an evaluation score based on this objective and actual data."

[0119] As described above, the system of the present invention provides a specific form for automating the evaluation process and improving the objectivity and efficiency of the evaluation.

[0120] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0121] Step 1:

[0122] The user enters the goals and performance data to be evaluated.

[0123] Input: Data entered by the user in the device evaluation form (e.g., "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1")

[0124] Action: The user opens a browser and accesses a specific URL. The user enters goal and performance data into an evaluation form and clicks the "Submit" button.

[0125] Output: The input data is temporarily stored on the terminal.

[0126] Step 2:

[0127] The terminal sends the entered data to the server.

[0128] Input: Data entered in the evaluation form

[0129] Operation: The device uses the browser's JavaScript code to convert the form data into JSON format. The converted data is sent to the server using the HTTPS protocol with SSL / TLS.

[0130] Output: JSON data sent to the server

[0131] Step 3:

[0132] The server receives, verifies, and stores the data.

[0133] Input: JSON data sent from the device

[0134] Operation: The server receives an HTTP request and checks the format of the received data and verifies required fields. Once verification is complete, the data is saved to the database. The data is then inserted into the appropriate table in the database using an SQL INSERT statement.

[0135] Output: Evaluation data stored in the database

[0136] Step 4:

[0137] The server activates a generative AI based on the stored data and begins the analysis process.

[0138] Input: Evaluation data stored in the database

[0139] Operation: The server executes a Python script and loads a machine learning model (e.g., scikit-learn or TensorFlow). It then passes data from a stored database to the model.

[0140] Output: Evaluation data received by the generative AI

[0141] Step 5:

[0142] Generative AI analyzes the data and generates a score based on evaluation criteria.

[0143] Input: Evaluation data passed to the generative AI

[0144] Operation: The generative AI analyzes data based on pre-defined evaluation criteria. For example, it might evaluate "5% cost reduction = 70 points." The score is stored in temporary memory.

[0145] Output: Generated evaluation score

[0146] Step 6:

[0147] The server saves the generated evaluation results.

[0148] Input: Evaluation score generated by a generative AI

[0149] Operation: The server receives the evaluation score and saves it back to the database. It executes an SQL query such as "INSERT INTO scoretable (project, score) VALUES ('project B', 70);".

[0150] Output: Evaluation scores stored in the database

[0151] Step 7:

[0152] The server sends the evaluation results to the terminal.

[0153] Input: Evaluation score stored in the database

[0154] Operation: The server generates an evaluation score as an HTTP response and sends the evaluation result to the terminal in JSON format.

[0155] Output: JSON data of the evaluation results sent to the terminal.

[0156] Step 8:

[0157] The device displays the evaluation results to the user.

[0158] Input: JSON data of evaluation results sent from the server

[0159] Operation: The device receives an HTTP response and parses the JSON response body using JavaScript code. The evaluation result is displayed in a UI component (e.g., the evaluation results section of the dashboard), visually informing the user of "Q1 sales growth rate evaluation: 70 points".

[0160] Output: Evaluation results displayed on the user's screen

[0161] The above describes the specific processing steps in the system of the present invention. This ensures objectivity and efficiency in evaluation, and realizes an accurate and rapid evaluation process.

[0162] (Application Example 1)

[0163] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0164] Traditional personnel evaluation and performance evaluation systems lacked objectivity and efficiency, often involving subjective judgments, leading to unfair evaluation results. Furthermore, the evaluation process was time-consuming and labor-intensive. In addition, performance evaluation in logistics center management was highly subjective, making efficient improvement measures difficult.

[0165] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0166] In this invention, the server includes means for the user to input target and performance data to be evaluated, means for the terminal to transmit the input data to the server, means for the server to receive and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, means for the terminal to display the evaluation results to the user, and means for logging, and means for generating an evaluation score using a generative AI that calculates performance based on the input data of targets and performance. This improves the objectivity and efficiency of the evaluation, enabling rapid and fair performance evaluation of the logistics center.

[0167] A "user" is the entity that accesses the system and inputs goal and performance data.

[0168] A "terminal" is a computer device used to send data entered by a user to a server.

[0169] A "server" is a computer device that stores data received from terminals, initiates the analysis process, generates evaluation results, and stores them.

[0170] "Generative AI" refers to artificial intelligence models that analyze input data and generate scores based on evaluation criteria.

[0171] "Evaluation criteria" refer to pre-set rules or standards that a generative AI follows when generating a score.

[0172] A "score" is an evaluation value generated by a generative AI based on evaluation criteria.

[0173] A "logging means" is a means that has the function of recording and saving operation logs such as evaluation processes and data reception and storage.

[0174] "Target and performance data" refers to the specific numerical targets and performance data entered by the user for evaluation.

[0175] "Results" refer to data on the actual outcomes achieved in relation to the goals.

[0176] "Data integrity" refers to the state in which received data remains accurate and unchanged from what was intended by the sender.

[0177] "Consistency" refers to a state where received data is consistent with other data and existing systems, and free from contradictions.

[0178] To implement this invention, it is necessary to construct a system in which users, terminals, and servers collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0179] User-side actions

[0180] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input specific objectives such as "Project A's objective is a 15% increase in sales" or actual performance data such as "Q1 sales increased by 10%."

[0181] Terminal-side operation

[0182] The terminal's role is to send data entered by the user to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP request. Data transmission is protected using security protocols such as SSL / TLS.

[0183] Server-side operation

[0184] The server's role is to receive and store data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server launches a generative AI. This uses a machine learning model implemented in a programming language such as Python.

[0185] The generative AI analyzes the input target and performance data and generates scores based on pre-set evaluation criteria. For example, if the evaluation criteria for sales growth rate are trained to be "10% increase = 85 points," the AI ​​will generate scores accordingly. The server stores the generated scores in a database.

[0186] Displaying Results

[0187] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" will be displayed.

[0188] A series of specific examples

[0189] For example, the following evaluation process is possible.

[0190] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0191] 2. The device sends this data to the server.

[0192] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0193] 4. The server activates the generative AI and analyzes the data.

[0194] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the server saves this evaluation score to the database.

[0195] 6. The server sends the evaluation score to the terminal.

[0196] 7. The device displays the evaluation score to the user.

[0197] Examples of prompts to input into a generative AI model

[0198] "Employee A's Q1 target was a 15% reduction in inventory. Their actual result was a 10% reduction. Please calculate their performance score."

[0199] Hardware and software to be used

[0200] Server: Uses Flask and SQLite for data processing and analysis.

[0201] Generative AI: Python and scikit-learn are used for score calculation.

[0202] Data protection: Uses SSL / TLS protocol.

[0203] Frontend: Utilizes a web interface optimized for smartphones.

[0204] As a result, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0205] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0206] Step 1: The user enters goal and performance data.

[0207] ---

[0208] Users access the system's evaluation form using their own devices and enter the evaluation target (e.g., "15% increase in sales") and performance data (e.g., "Q1 sales increased by 10%"). The entered data is saved on the device.

[0209] Step 2: The device sends data to the server.

[0210] ---

[0211] The terminal formats the data entered by the user into the appropriate format and sends it to the server using an HTTP request. SSL / TLS protocol is used to protect the data. Input data includes numerical data for targets and actual results. The output is the data sent to the server.

[0212] Step 3: The server receives and stores the data.

[0213] ---

[0214] The server receives data sent from the terminal. It then checks the integrity and validity of the received data. Once the data is deemed acceptable, it saves it to a database (such as SQLite). In this case, the input is the data sent from the terminal, and the output is the data stored in the database.

[0215] Step 4: The server starts the generative AI model and begins the analysis process.

[0216] ---

[0217] The server launches a generative AI model using data stored in the database. This AI model is implemented using Python or scikit-learn. The generative AI analyzes the data based on pre-defined evaluation criteria and generates a score. The input is stored target and performance data, and the output is the generated evaluation score.

[0218] Step 5: The server saves the generated evaluation score.

[0219] ---

[0220] The evaluation score generated by the generative AI is then saved again to the database by the server. The input is the score generated by the generative AI, and the output is the score saved in the database.

[0221] Step 6: The server sends the evaluation results to the terminal.

[0222] ---

[0223] The server sends the generated evaluation score to the terminal. It returns data containing the evaluation score in the HTTP response. The input is the score stored in the database, and the output is the score data sent to the terminal.

[0224] Step 7: The device displays the evaluation results to the user.

[0225] ---

[0226] The terminal displays the evaluation results received from the server on the user's screen. Specifically, evaluation results such as "Q1 Sales Growth Rate Evaluation: 85 points" can be seen through the dashboard function. The input is the score data sent from the server, and the output is the evaluation result displayed on the user's screen.

[0227] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0228] To implement the present invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion engine collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which the user inputs goal and performance data, and the generative AI and emotion engine analyze this data to generate an evaluation score.

[0229] User-side actions

[0230] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input data such as "Project A's objective is a 15% increase in sales" or "Q1 sales increased by 10%."

[0231] Terminal-side operation

[0232] The terminal's role is to send user-entered data to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP POST request. SSL / TLS is used to encrypt the data transmission during this process.

[0233] Server-side operation

[0234] The server is responsible for receiving and storing data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server activates the generative AI and emotion engine. This uses machine learning models and emotion analysis models implemented in programming languages ​​such as Python.

[0235] How generative AI and emotion engines work

[0236] The generative AI analyzes the input goal and performance data and generates a score based on pre-set evaluation criteria. Meanwhile, the emotion engine analyzes the user's facial expressions, voice, and input speed during input to recognize emotional data. This emotional data is incorporated into the evaluation process by the generative AI to generate a more accurate score that takes the user's emotional state into account.

[0237] For example, if the AI ​​is trained with a rating system where "10% increase in sales = 85 points," it will generate a score by incorporating user emotional data. If the emotional data indicates the user's sense of effort or stress level, that information will be reflected in the evaluation.

[0238] Saving and displaying results

[0239] The server stores the generated evaluation results and adjustments based on sentiment data in a database. When saving, it also saves metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data, in addition to the score.

[0240] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points (with sentiment adjustment)" will be displayed.

[0241] Specific example

[0242] For example, the following evaluation process is possible.

[0243] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0244] 2. The device sends this data to the server.

[0245] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0246] 4. The server activates the generative AI and emotion engine, and analyzes the data and user emotion data.

[0247] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the emotion engine recognizes "the user's high stress state" and generates a final score of "75 points" as a correction.

[0248] 6. The server saves an evaluation score of 75 points to the database.

[0249] 7. The server sends the evaluation score to the terminal.

[0250] 8. The device displays the evaluation score to the user.

[0251] Through the above process, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, by incorporating an emotion engine, the user's emotional state is reflected in the evaluation, enabling a more comprehensive and human-centered assessment. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] Users input the target goals and performance data to be evaluated into their terminals. Specifically, users log into the system, access the evaluation form, and input data such as "Project A's goal is a 15% increase in sales" or "Q1 sales increased by 10%."

[0255] Step 2:

[0256] The terminal sends the data entered by the user to the server. After the input is complete, the terminal converts the data to the appropriate format and sends it to the server using an HTTP POST request. At this time, the data is encrypted using SSL / TLS.

[0257] Step 3:

[0258] The server receives data sent from the terminal. The server first checks the completeness and integrity of the received data, and if there are no problems, it saves it to the database. If an error occurs, it returns an error message to the terminal.

[0259] Step 4:

[0260] The server activates the emotion engine. The emotion engine on the server collects data such as the user's facial expressions, voice, and input speed in real time and analyzes the user's emotional state. The analysis results are stored as emotion data.

[0261] Step 5:

[0262] The server launches a generative AI based on the stored data. The server then calls an evaluation machine learning model and starts the evaluation process. Specifically, a model implemented in a programming language such as Python analyzes the target data.

[0263] Step 6:

[0264] Generative AI analyzes data and generates scores based on evaluation criteria. For example, it might generate a score of "85 points" based on an evaluation criterion such as "10% sales growth rate."

[0265] Step 7:

[0266] The server adjusts the score generated based on emotional data. For example, if the user's stress level is high, 5 points are added to the score, and the final score is calculated taking into account the information obtained from the emotional engine.

[0267] Step 8:

[0268] The server saves the generated evaluation results to a database. When saving, in addition to the score, metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data are also saved.

[0269] Step 9:

[0270] The server sends the evaluation results to the terminal. The server returns the evaluation results to the terminal as an HTTP response. The terminal receives this response.

[0271] Step 10:

[0272] The device displays the evaluation results to the user. Specifically, when the user accesses the dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points (with sentiment adjustment)" is displayed. The user can then use this information to take further action or make decisions.

[0273] Through these steps, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, by incorporating an emotion engine, the user's emotional state is reflected in the evaluation, enabling a more comprehensive and human-centered assessment. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0274] (Example 2)

[0275] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0276] Modern evaluation systems suffer from problems with subjectivity and efficiency in the evaluation process. Specifically, traditional evaluation systems rely heavily on the subjectivity of evaluators, often lacking consistency and objectivity in their assessments. Furthermore, proper analysis of input data and rapid provision of results require considerable effort and time, making efficient process management difficult. In addition, because they do not consider the user's emotional state, evaluation results do not accurately reflect the user's actual effort or stress level, which is a significant challenge.

[0277] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for verifying the integrity and consistency of the stored data, means for starting a generative AI and an emotion analysis engine and initiating data analysis, and means for generating a score based on evaluation criteria and reflecting the user's emotion data in the evaluation. This enhances the objectivity and consistency of the evaluation and enables a rapid and effective evaluation process. Furthermore, by considering the user's emotional state, a more human-centered and comprehensive evaluation becomes possible.

[0278] A "user" is an individual or organization that accesses the system and enters goal and performance data.

[0279] A "terminal" is a computer device used by a user to input data and send it to a server.

[0280] A "server" is a device that receives and stores data sent from users and terminals, and performs data analysis by activating generative AI and emotion analysis engines.

[0281] "Target data" refers to data that shows the specific goals and objectives that are being evaluated.

[0282] "Performance data" refers to data that shows the actual results and outcomes in relation to the target.

[0283] A "generative AI" is a machine learning model used to generate an evaluation score based on the input target and performance data.

[0284] An "emotion analysis engine" is a system that analyzes data such as the user's expression, voice, input speed, etc., and reflects the user's emotional state in the evaluation.

[0285] An "evaluation criterion" is a pre-set criterion or rule used by the generative AI when generating an evaluation score.

[0286] A "score" is a numerical representation of the evaluation result generated by the generative AI based on the evaluation criterion.

[0287] "Metadata" is additional information such as the generation date and time of the evaluation result, evaluation criterion, and emotion data.

[0288] To implement this invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion analysis engine cooperate to perform an evaluation process. This system improves the objectivity and efficiency of the evaluation through the process in which the user inputs target and performance data, analyzes based on this, and generates an evaluation score.

[0289] User-side operations

[0290] The user accesses the system and inputs the target and performance data of the evaluation object. For example, the user uses a web browser to access the evaluation form of the system and inputs data such as "Goal of Project A: 15% increase in sales", "Achievement: 10% increase in sales in Q1".

[0291] Terminal-side operations

[0292] The terminal sends the data entered by the user to the server. After the user has finished entering the data, the terminal formats this data into JSON format and sends it to the server using an HTTP POST request. SSL / TLS is used to encrypt the data during this process to ensure security.

[0293] Server-side operation

[0294] The server receives and stores data sent from the terminal. First, the server verifies the integrity and validity of the received data. For example, it checks the hash value of the data to ensure it hasn't been tampered with. Once verification is complete, the server saves the data to the database.

[0295] How generative AI and emotion analysis engines work

[0296] After the data has been saved, the server starts the generative AI and sentiment analysis engine. The generative AI uses a Python machine learning model, and the sentiment analysis engine also utilizes Python libraries. These models are then started, and data analysis begins.

[0297] Generative AI analyzes input data based on pre-trained evaluation criteria and generates an evaluation score. For example, an evaluation criterion such as "10% increase in sales = 85 points" is set. On the other hand, the emotion analysis engine generates emotion data by analyzing the user's facial expressions, voice, input speed, etc. In this invention, a more accurate evaluation score is generated by incorporating the user's emotion data into the evaluation.

[0298] Saving and displaying results

[0299] The server saves the generated evaluation results and related metadata (such as evaluation date and time, evaluation criteria, sentiment data, etc.) in the database. After the recording is completed, the server sends the evaluation results to the terminal. The terminal receives the sent evaluation results and displays them on the user's screen. For example, when the user accesses the system dashboard, the results are displayed like "Q1 sales growth rate evaluation: 90 points (with sentiment correction)".

[0300] Specific example

[0301] The following example is given as a specific evaluation process.

[0302] 1. The user inputs data such as "Goal of Project B: 10% cost reduction in the department" and "Achievement: 5% cost reduction in Q1" into the terminal.

[0303] 2. The terminal converts this data into JSON format and sends it to the server.

[0304] 3. After receiving the data, the server checks its completeness and consistency and then saves it in the database.

[0305] 4. The server starts the generative AI and sentiment analysis engine and begins data analysis.

[0306] 5. The generative AI evaluates that "5% cost reduction = 70 points", and the sentiment analysis engine recognizes the user's high-stress state, resulting in a final score of "75 points".

[0307] 6. The server saves the evaluation result of 75 points and related metadata in the database.

[0308] 7. The server sends the evaluation results to the terminal.

[0309] 8. The terminal displays the evaluation score on the user screen, showing "Q1 cost reduction evaluation: 75 points (with sentiment correction)".

[0310] Through this process, users can obtain quick and objective evaluation results. The introduction of an emotion analysis engine enables a comprehensive evaluation that reflects the user's emotional state, significantly reducing effort and time.

[0311] Example of a prompt

[0312] For example, here are some examples of prompt statements to input into a generative AI model:

[0313] "Project A's goal was a 15% increase in sales. Sales increased by 10% in the first quarter. Based on user input speed and facial expressions, it appears the user was under high stress during the evaluation process. Please generate the optimal evaluation score based on this information."

[0314] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0315] Step 1:

[0316] The user enters the goals and performance data to be evaluated.

[0317] Specific operation: The user accesses the system's evaluation form using a web browser and enters data such as "Project A's goal: 15% increase in sales" and "Actual results: 10% increase in sales in Q1".

[0318] Input: Target data and performance data.

[0319] Output: Data entered into the evaluation form.

[0320] Step 2:

[0321] The terminal sends the data entered by the user to the server.

[0322] Specific operation: The terminal formats this data into JSON format and sends it to the server via an HTTP POST request. SSL / TLS is used to encrypt the data during this process.

[0323] Input: Target data and performance data formatted in JSON format.

[0324] Output: Encrypted HTTP POST request.

[0325] Step 3:

[0326] The server receives and stores the data sent from the terminal.

[0327] Specific operation: The server first verifies the integrity and consistency of the received data and checks the data's hash value. Once verification is complete, it saves the data to the database.

[0328] Input: Encrypted data.

[0329] Output: Data stored in the database.

[0330] Step 4:

[0331] The server starts up the generative AI and the emotion analysis engine.

[0332] Specific operation: The server runs a generative AI model and sentiment analysis engine via a Python script.

[0333] Input: Saved data.

[0334] Output: An AI model and sentiment analysis engine ready for analysis.

[0335] Step 5:

[0336] Generative AI analyzes input data based on evaluation criteria and generates an evaluation score.

[0337] Specific operation: The generative AI analyzes the data based on pre-trained evaluation criteria. The rule used as a prompt is "10% increase in sales = 85 points".

[0338] Input: Evaluation criteria and saved data.

[0339] Output: Primary evaluation score.

[0340] Step 6:

[0341] The emotion analysis engine analyzes the user's emotional data.

[0342] Specific operation: The emotion analysis engine generates emotion data from the user's facial expressions, voice, input speed, etc.

[0343] Input: User behavior data.

[0344] Output: Sentiment data.

[0345] Step 7:

[0346] The generative AI and the emotion analysis engine work together to generate the final evaluation score.

[0347] Specific operation: The generative AI calculates the final evaluation score by reflecting the emotional data. For example, it corrects an initial evaluation score of 85 points to 90 points.

[0348] Input: Primary evaluation score and sentiment data.

[0349] Output: Final evaluation score.

[0350] Step 8:

[0351] The server stores the generated evaluation results and associated metadata.

[0352] Specific operation: The server stores evaluation results and related metadata (evaluation date and time, evaluation criteria, sentiment data, etc.) in the database.

[0353] Input: Final rating score and metadata.

[0354] Output: Evaluation results and metadata stored in the database.

[0355] Step 9:

[0356] The server sends the evaluation results to the terminal.

[0357] Specific operation: The server sends the evaluation results to the terminal as an HTTP response.

[0358] Input: Final rating score and metadata.

[0359] Output: The evaluation results that were sent.

[0360] Step 10:

[0361] The device displays the evaluation results on the user's screen.

[0362] Specific operation: The terminal analyzes the submitted evaluation results and displays "Q1 Sales Growth Rate Evaluation: 90 points (with sentiment adjustment)" on the user's screen.

[0363] Input: Evaluation results sent from the server.

[0364] Output: The evaluation results displayed to the user.

[0365] (Application Example 2)

[0366] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0367] In modern performance evaluation systems, objectivity and accuracy are challenges when evaluating users' goals and performance data. Furthermore, traditional systems often fail to reflect users' emotional states in evaluations, resulting in evaluations that tend to be purely numerical. This makes fair evaluation and comprehensive, human-centered assessments difficult.

[0368] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for starting a generative AI and an emotion recognition engine and initiating an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, and means for the emotion recognition engine to acquire the user's emotion data and reflect it in the evaluation. This makes it possible to perform a more comprehensive and fair evaluation that takes into account the user's emotion data in addition to their goal and performance data.

[0369] A "user" is an individual or organization that inputs the objectives and performance data to be evaluated.

[0370] A "terminal" is a device that sends data entered by the user to a server and receives and displays evaluation results from the server.

[0371] A "server" is a computing system that receives, stores, and analyzes data sent from a terminal.

[0372] "Generative AI" is artificial intelligence that analyzes goal and performance data entered by the user and generates scores based on pre-trained evaluation criteria.

[0373] An "emotion recognition engine" is an analytical engine that acquires user emotion data and incorporates it into evaluations.

[0374] "Data" refers to information about goals and performance entered by the user.

[0375] A "score" is an evaluation value generated by a generative AI as a result of analyzing data based on evaluation criteria.

[0376] "Emotional data" refers to information about a user's emotional state, obtained from their facial expressions, voice, and other sources.

[0377] "Evaluation criteria" are predetermined standards based on how a generative AI generates a score.

[0378] "Integrity" refers to the check items to ensure that the entered data has not been tampered with.

[0379] "Consistency" refers to the check items that verify whether the entered data conforms to the specified format and content.

[0380] To implement this invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion recognition engine collaborate to perform the evaluation process. The detailed operation of this system is described below.

[0381] User-side actions

[0382] Users access the system and input the objectives and performance data to be evaluated. Specifically, users input data such as "Project A's objective is to reduce the product defect rate by 10%" or "Actual: Material defect rate reduced by 6%" into the terminal. After input, the terminal formats the data into the appropriate format and sends it to the server.

[0383] Terminal-side operation

[0384] The terminal's role is to send data entered by the user to the server. This process uses an HTTP POST request and encrypts the data transmission using SSL / TLS. The transmitted data includes the user's goals and performance data.

[0385] Server-side operation

[0386] The server receives data sent from the terminal and first checks its integrity and consistency. This includes verifying that the data has not been tampered with and that it conforms to the correct format. After verification is complete, the data is saved to the database.

[0387] After saving is complete, the server starts the generative AI and emotion recognition engine. This process uses machine learning models (e.g., linear regression models and neural networks) and emotion analysis models implemented in programming languages ​​such as Python. The generative AI analyzes the input data based on pre-trained evaluation criteria and generates a score. Meanwhile, the emotion recognition engine analyzes emotion data obtained from the user's facial expressions and voice and incorporates it into the evaluation.

[0388] Specific operation of the emotion recognition engine

[0389] The emotion recognition engine uses face recognition (face_recognition) and speech recognition (speech_recognition) libraries to analyze the user's facial expressions and voice data. For example, it uses a camera to capture the user's facial expressions as images and recognize their emotions. It also acquires voice data and performs speech recognition to analyze emotions from the user's voice. The analysis results are reflected in a score as an emotional state such as "positive," "neutral," or "negative."

[0390] Saving and displaying results

[0391] The server stores the generated evaluation results and adjustments based on sentiment data in a database. The data stored includes metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data, in addition to the score. After processing is complete, the server sends the evaluation results to the terminal, and the terminal displays the evaluation results on the user's screen. Specifically, it will display something like "Evaluation result: 75 points (with sentiment adjustment)."

[0392] Specific example

[0393] For example, the following evaluation process is possible:

[0394] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0395] 2. The device sends this data to the server.

[0396] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0397] 4. The server activates the generative AI and emotion recognition engine, and analyzes the data and user emotion data.

[0398] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the emotion recognition engine recognizes "the user's high stress state" and generates a final score of "75 points" as a correction.

[0399] 6. The server saves an evaluation score of 75 points to the database.

[0400] 7. The server sends the evaluation score to the terminal.

[0401] 8. The device displays the evaluation score to the user.

[0402] Example of a prompt

[0403] The following are examples of prompts to input into a generative AI model:

[0404] The goal of Project A is to reduce the product defect rate by 10%.

[0405] Results: Material defect rate reduced by 6%

[0406] Facial expression analysis result: positive

[0407] Voice analysis results: neutral

[0408] In this way, combining generative AI with an emotion recognition engine can improve the objectivity and accuracy of evaluations of user goal and performance data. Furthermore, by incorporating emotional data, a comprehensive evaluation that reflects the user's emotional state becomes possible.

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The user inputs the target and performance data to be evaluated into the terminal. Specifically, they enter data such as "Project A's target is a 10% reduction in product defect rate" or "Actual: Material defect rate reduced by 6%" into the designated input fields. This completes the data input process (input: target and performance data, output: formatted data).

[0412] Step 2:

[0413] The terminal sends the goal and performance data entered by the user to the server. The transmission uses an HTTP POST request and SSL / TLS to encrypt the data (input: formatted data, output: data sent to the server).

[0414] Step 3:

[0415] The server receives data sent from the terminal and checks its integrity and consistency. This includes checking for data tampering and verifying format compliance. Once verification is complete, the data is stored in the database (input: sent data, output: verified data).

[0416] Step 4:

[0417] The server activates the generative AI and emotion recognition engine based on the stored data. First, the generative AI analyzes the input data and generates a score based on pre-trained evaluation criteria (input: stored data, output: initial evaluation score).

[0418] Step 5:

[0419] The emotion recognition engine acquires and analyzes the user's emotional data. This process involves using the face recognition library (face_recognition) to acquire facial expression data and the speech recognition library (speech_recognition) to analyze speech data. The analysis results are obtained as emotional states such as "positive," "neutral," and "negative" (input: image and audio data, output: emotional data).

[0420] Step 6:

[0421] The server adjusts the generative AI's score based on the analyzed emotional data. For example, if the generative AI evaluates "5% cost reduction = 70 points" and the emotional recognition engine recognizes "the user is in a high-stress state," it will generate a final score of "75 points" as a correction (input: initial evaluation score, emotional data; output: corrected final score).

[0422] Step 7:

[0423] The server stores the generated evaluation results and adjustments based on sentiment data in a database. The data stored includes metadata such as the evaluation date and time, evaluation criteria, and sentiment data, in addition to the score (input: final evaluation score, output: stored evaluation data).

[0424] Step 8:

[0425] The server sends the evaluation results to the terminal, and the terminal displays the evaluation results to the user. Specifically, it will display something like "Evaluation result: 75 points (with sentiment adjustment)" (Input: saved evaluation data, Output: user's display screen).

[0426] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0427] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0428] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0429] [Second Embodiment]

[0430] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0431] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0432] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0433] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0434] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0435] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0436] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0437] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0438] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0439] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0440] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0441] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0442] To implement this invention, it is necessary to construct a system in which users, terminals, and servers collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0443] User-side actions

[0444] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input specific objectives such as "Project A's objective is a 15% increase in sales" or actual performance data such as "Q1 sales increased by 10%."

[0445] Terminal-side operation

[0446] The terminal's role is to send data entered by the user to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP request. Data transmission is protected using security protocols such as SSL / TLS.

[0447] Server-side operation

[0448] The server's role is to receive and store data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server launches a generative AI. This uses a machine learning model implemented in a programming language such as Python.

[0449] The generative AI analyzes the input target and performance data and generates scores based on pre-set evaluation criteria. For example, if the evaluation criteria for sales growth rate are trained to be "10% increase = 85 points," the AI ​​will generate scores accordingly. The server stores the generated scores in a database.

[0450] Displaying Results

[0451] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" will be displayed.

[0452] Specific example

[0453] For example, the following evaluation process is possible.

[0454] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0455] 2. The device sends this data to the server.

[0456] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0457] 4. The server activates the generative AI and analyzes the data.

[0458] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the server saves this evaluation score to the database.

[0459] 6. The server sends the evaluation score to the terminal.

[0460] 7. The device displays the evaluation score to the user.

[0461] Through the above process, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] Users input the target goals and performance data to be evaluated into their terminal. Specifically, after logging in, users access the evaluation form and input data such as "Project A's goal is a 15% increase in sales" or "Q1 sales increased by 10%."

[0465] Step 2:

[0466] The terminal sends data entered by the user to the server. The terminal converts the data to an appropriate format and sends it to the server using an HTTP POST request or similar method. During this process, SSL / TLS is used to encrypt the data transmission.

[0467] Step 3:

[0468] The server receives data sent from the terminal. The server verifies the integrity and validity of the data and returns an error message to the terminal if there are any errors. If there are no problems, the server saves this data to the database.

[0469] Step 4:

[0470] The server launches a generative AI based on the stored data. Specifically, the server calls a machine learning model implemented in Python or another language and starts the evaluation process.

[0471] Step 5:

[0472] Generative AI analyzes data and generates a score based on evaluation criteria. For example, if the input is "sales growth rate of 10%", a pre-trained model will analyze this and generate a score of "85 points".

[0473] Step 6:

[0474] The server saves the generated evaluation results to a database. When saving, metadata such as the date and time the evaluation was performed and the evaluation criteria are also saved along with the score.

[0475] Step 7:

[0476] The server sends the evaluation results to the terminal. The server returns the evaluation results to the terminal as an HTTP response. The terminal receives this response.

[0477] Step 8:

[0478] The device displays the evaluation results to the user. Specifically, when the user accesses the dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" is displayed. Based on this information, the user can take further actions or make decisions.

[0479] Through these steps, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0480] (Example 1)

[0481] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0482] Existing evaluation systems often lack objectivity and consistency in their assessments, and subjectivity is particularly likely to creep into the analysis and scoring of evaluation data, making fair evaluation difficult. Furthermore, the evaluation process is often manual, resulting in high time and effort requirements and low efficiency. Additionally, insufficient verification of the integrity and completeness of input data can lead to inaccurate evaluation results.

[0483] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0484] In this invention, the server includes means for the user to input target and performance data to be evaluated, means for the terminal to transmit the input data to the server, means for the server to receive, verify, and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, means for the server to transmit the evaluation results to the terminal, and means for the terminal to display the evaluation results to the user. This ensures objectivity and consistency in evaluation and enables an efficient and accurate evaluation process.

[0485] A "user" refers to an individual or legal entity that is responsible for inputting goal and performance data using the evaluation system.

[0486] "Terminal" refers to a device (e.g., PC, smartphone) that a user uses to access the evaluation system and input and transmit data.

[0487] A "server" refers to a central processing unit that receives data sent from terminals and performs storage and analysis processes.

[0488] "Goal and performance data" refers to numerical or string data entered by the user that indicates specific goals subject to evaluation and their achievement status.

[0489] "Transmission" refers to the act of a terminal transferring data entered by the user to a server.

[0490] "Receiving" refers to the act of a server receiving data sent from a terminal.

[0491] "Verification" refers to the process of confirming the integrity and validity of the data received by the server.

[0492] "Saving" refers to the act of a server recording received data or generated evaluation results in a database.

[0493] "Generative AI" refers to artificial intelligence models trained to perform data analysis and generate evaluation scores.

[0494] The "analysis process" refers to a series of processes by which a generative AI analyzes data and generates a score based on evaluation criteria.

[0495] "Evaluation criteria" refers to pre-set standards used by generative AI when scoring data.

[0496] "Evaluation results" refer to the scores generated by a generative AI based on evaluation criteria after data analysis.

[0497] "Display" refers to the act of showing the evaluation results received by the terminal from the server on the screen in a format that the user can see.

[0498] This invention improves the objectivity and efficiency of evaluation by constructing a system in which users, terminals, and servers collaborate to perform the evaluation process. In this system, users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0499] User-side actions

[0500] Users access the system's evaluation form using their own devices, such as PCs or smartphones. In the evaluation form, users are responsible for entering goal and performance data. For example, a user might enter goal data such as "Project A's goal is a 15% increase in sales" or performance data such as "Q1 sales increased by 10%." The data entered by users plays a crucial role in the system's evaluation process.

[0501] Terminal-side operation

[0502] The terminal's role is to send data entered by the user to the server. Once the user finishes entering data into the evaluation form, the terminal formats this data into an appropriate format (e.g., JSON or XML) and sends it to the server using an HTTP request. During this process, security protocols such as SSL / TLS are used to protect the data during transmission.

[0503] Server-side operation

[0504] The server is the central processing unit that receives data sent from terminals and performs storage and analysis processes. First, the server checks the integrity and consistency of the received data. This verification includes checking the data format and verifying required fields. Once verification is complete, the data is stored in the database. This is done using database operation commands such as SQL.

[0505] Once data is saved, the server launches a generative AI. This generative AI is implemented as a Python script and uses a machine learning model trained for specific data analysis and scoring. The server passes the saved data to the AI ​​model for analysis. The generative AI analyzes the received data and generates a score based on pre-defined evaluation criteria. For example, if the evaluation criterion for sales growth rate is set to "10% increase = 85 points," the AI ​​will calculate the score accordingly.

[0506] The evaluation score generated as a result of the analysis is saved again to the database. After the evaluation score is saved, the server sends the evaluation result to the terminal. The terminal receives this data and displays the evaluation result on the user's screen.

[0507] Specific example

[0508] For example, the following evaluation process is possible:

[0509] 1. The user opens a browser on their device and accesses a specific URL (e.g., https: / / example.com / evaluation). They then enter the following data into the displayed evaluation form: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0510] 2. When the device clicks the "Submit" button, the browser's JavaScript code converts the form data into JSON format and sends a POST request to the server using the HTTPS protocol with SSL / TLS.

[0511] 3. The server receives the request and verifies the format and content of the received data. It checks for format errors and missing required fields.

[0512] 4. The server establishes a database connection and inserts the performance data into the appropriate table in the database using an SQL INSERT statement.

[0513] 5. Once data saving is complete, the server executes a Python script to load a machine learning model (e.g., scikit-learn or TensorFlow). The saved database data is then passed to the model.

[0514] 6. The generating AI inputs data into the model and generates an evaluation score, such as "5% cost reduction = 70 points". The score is stored in temporary memory.

[0515] 7. The server receives the evaluation score and executes an SQL query such as "INSERT INTO scoretable (project, score) VALUES ('project B', 70);" to save the score to the database.

[0516] 8. After the save operation, the server creates an HTTP response containing the evaluation score on the terminal and sends the evaluation result in JSON format in the response body.

[0517] 9. The device receives the HTTP response and parses the JSON response body using JavaScript. The evaluation result is displayed in a UI component (e.g., the evaluation result section of the dashboard), visually informing the user that "Q1 sales growth rate evaluation: 70 points".

[0518] Examples of prompt statements are as follows:

[0519] "Project B's objective is a 10% cost reduction for the department, and the actual result was a 5% cost reduction in Q1. Please generate an evaluation score based on this objective and actual data."

[0520] As described above, the system of the present invention provides a specific form for automating the evaluation process and improving the objectivity and efficiency of the evaluation.

[0521] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0522] Step 1:

[0523] The user enters the goals and performance data to be evaluated.

[0524] Input: Data entered by the user in the device evaluation form (e.g., "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1")

[0525] Action: The user opens a browser and accesses a specific URL. The user enters goal and performance data into an evaluation form and clicks the "Submit" button.

[0526] Output: The input data is temporarily stored on the terminal.

[0527] Step 2:

[0528] The terminal sends the entered data to the server.

[0529] Input: Data entered in the evaluation form

[0530] Operation: The device uses the browser's JavaScript code to convert the form data into JSON format. The converted data is sent to the server using the HTTPS protocol with SSL / TLS.

[0531] Output: JSON data sent to the server

[0532] Step 3:

[0533] The server receives, verifies, and stores the data.

[0534] Input: JSON data sent from the device

[0535] Operation: The server receives an HTTP request and checks the format of the received data and verifies required fields. Once verification is complete, the data is saved to the database. The data is then inserted into the appropriate table in the database using an SQL INSERT statement.

[0536] Output: Evaluation data stored in the database

[0537] Step 4:

[0538] The server activates a generative AI based on the stored data and begins the analysis process.

[0539] Input: Evaluation data stored in the database

[0540] Operation: The server executes a Python script and loads a machine learning model (e.g., scikit-learn or TensorFlow). It then passes data from a stored database to the model.

[0541] Output: Evaluation data received by the generative AI

[0542] Step 5:

[0543] Generative AI analyzes the data and generates a score based on evaluation criteria.

[0544] Input: Evaluation data passed to the generative AI

[0545] Operation: The generative AI analyzes data based on pre-defined evaluation criteria. For example, it might evaluate "5% cost reduction = 70 points." The score is stored in temporary memory.

[0546] Output: Generated evaluation score

[0547] Step 6:

[0548] The server saves the generated evaluation results.

[0549] Input: Evaluation score generated by a generative AI

[0550] Operation: The server receives the evaluation score and saves it back to the database. It executes an SQL query such as "INSERT INTO scoretable (project, score) VALUES ('project B', 70);".

[0551] Output: Evaluation scores stored in the database

[0552] Step 7:

[0553] The server sends the evaluation results to the terminal.

[0554] Input: Evaluation score stored in the database

[0555] Operation: The server generates an evaluation score as an HTTP response and sends the evaluation result to the terminal in JSON format.

[0556] Output: JSON data of the evaluation results sent to the terminal.

[0557] Step 8:

[0558] The device displays the evaluation results to the user.

[0559] Input: JSON data of evaluation results sent from the server

[0560] Operation: The device receives an HTTP response and parses the JSON response body using JavaScript code. The evaluation result is displayed in a UI component (e.g., the evaluation results section of the dashboard), visually informing the user of "Q1 sales growth rate evaluation: 70 points".

[0561] Output: Evaluation results displayed on the user's screen

[0562] The above describes the specific processing steps in the system of the present invention. This ensures objectivity and efficiency in evaluation, and realizes an accurate and rapid evaluation process.

[0563] (Application Example 1)

[0564] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0565] Traditional personnel evaluation and performance evaluation systems lacked objectivity and efficiency, often involving subjective judgments, leading to unfair evaluation results. Furthermore, the evaluation process was time-consuming and labor-intensive. In addition, performance evaluation in logistics center management was highly subjective, making efficient improvement measures difficult.

[0566] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0567] In this invention, the server includes means for the user to input target and performance data to be evaluated, means for the terminal to transmit the input data to the server, means for the server to receive and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, means for the terminal to display the evaluation results to the user, and means for logging, and means for generating an evaluation score using a generative AI that calculates performance based on the input data of targets and performance. This improves the objectivity and efficiency of the evaluation, enabling rapid and fair performance evaluation of the logistics center.

[0568] A "user" is the entity that accesses the system and inputs goal and performance data.

[0569] A "terminal" is a computer device used to send data entered by a user to a server.

[0570] A "server" is a computer device that stores data received from terminals, initiates the analysis process, generates evaluation results, and stores them.

[0571] "Generative AI" refers to artificial intelligence models that analyze input data and generate scores based on evaluation criteria.

[0572] "Evaluation criteria" refer to pre-set rules or standards that a generative AI follows when generating a score.

[0573] A "score" is an evaluation value generated by a generative AI based on evaluation criteria.

[0574] A "logging means" is a means that has the function of recording and saving operation logs such as evaluation processes and data reception and storage.

[0575] "Target and performance data" refers to the specific numerical targets and performance data entered by the user for evaluation.

[0576] "Results" refer to data on the actual outcomes achieved in relation to the goals.

[0577] "Data integrity" refers to the state in which received data remains accurate and unchanged from what was intended by the sender.

[0578] "Consistency" refers to a state where received data is consistent with other data and existing systems, and free from contradictions.

[0579] To implement this invention, it is necessary to construct a system in which users, terminals, and servers collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0580] User-side actions

[0581] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input specific objectives such as "Project A's objective is a 15% increase in sales" or actual performance data such as "Q1 sales increased by 10%."

[0582] Terminal-side operation

[0583] The terminal's role is to send data entered by the user to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP request. Data transmission is protected using security protocols such as SSL / TLS.

[0584] Server-side operation

[0585] The server's role is to receive and store data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server launches a generative AI. This uses a machine learning model implemented in a programming language such as Python.

[0586] The generative AI analyzes the input target and performance data and generates scores based on pre-set evaluation criteria. For example, if the evaluation criteria for sales growth rate are trained to be "10% increase = 85 points," the AI ​​will generate scores accordingly. The server stores the generated scores in a database.

[0587] Displaying Results

[0588] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" will be displayed.

[0589] A series of specific examples

[0590] For example, the following evaluation process is possible.

[0591] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0592] 2. The device sends this data to the server.

[0593] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0594] 4. The server activates the generative AI and analyzes the data.

[0595] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the server saves this evaluation score to the database.

[0596] 6. The server sends the evaluation score to the terminal.

[0597] 7. The device displays the evaluation score to the user.

[0598] Examples of prompts to input into a generative AI model

[0599] "Employee A's Q1 target was a 15% reduction in inventory. Their actual result was a 10% reduction. Please calculate their performance score."

[0600] Hardware and software to be used

[0601] Server: Uses Flask and SQLite for data processing and analysis.

[0602] Generative AI: Python and scikit-learn are used for score calculation.

[0603] Data protection: Uses SSL / TLS protocol.

[0604] Frontend: Utilizes a web interface optimized for smartphones.

[0605] As a result, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0606] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0607] Step 1: The user enters goal and performance data.

[0608] ---

[0609] Users access the system's evaluation form using their own devices and enter the evaluation target (e.g., "15% increase in sales") and performance data (e.g., "Q1 sales increased by 10%"). The entered data is saved on the device.

[0610] Step 2: The device sends data to the server.

[0611] ---

[0612] The terminal formats the data entered by the user into the appropriate format and sends it to the server using an HTTP request. SSL / TLS protocol is used to protect the data. Input data includes numerical data for targets and actual results. The output is the data sent to the server.

[0613] Step 3: The server receives and stores the data.

[0614] ---

[0615] The server receives data sent from the terminal. It then checks the integrity and validity of the received data. Once the data is deemed acceptable, it saves it to a database (such as SQLite). In this case, the input is the data sent from the terminal, and the output is the data stored in the database.

[0616] Step 4: The server starts the generative AI model and begins the analysis process.

[0617] ---

[0618] The server launches a generative AI model using data stored in the database. This AI model is implemented using Python or scikit-learn. The generative AI analyzes the data based on pre-defined evaluation criteria and generates a score. The input is stored target and performance data, and the output is the generated evaluation score.

[0619] Step 5: The server saves the generated evaluation score.

[0620] ---

[0621] The evaluation score generated by the generative AI is then saved again to the database by the server. The input is the score generated by the generative AI, and the output is the score saved in the database.

[0622] Step 6: The server sends the evaluation results to the terminal.

[0623] ---

[0624] The server sends the generated evaluation score to the terminal. It returns data containing the evaluation score in an HTTP response. The input is the score stored in the database, and the output is the score data sent to the terminal.

[0625] Step 7: The device displays the evaluation results to the user.

[0626] ---

[0627] The terminal displays the evaluation results received from the server on the user's screen. Specifically, evaluation results such as "Q1 Sales Growth Rate Evaluation: 85 points" can be seen through the dashboard function. The input is the score data sent from the server, and the output is the evaluation result displayed on the user's screen.

[0628] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0629] To implement the present invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion engine collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which the user inputs goal and performance data, and the generative AI and emotion engine analyze this data to generate an evaluation score.

[0630] User-side actions

[0631] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input data such as "Project A's objective is a 15% increase in sales" or "Q1 sales increased by 10%."

[0632] Terminal-side operation

[0633] The terminal's role is to send user-entered data to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP POST request. SSL / TLS is used to encrypt the data transmission during this process.

[0634] Server-side operation

[0635] The server is responsible for receiving and storing data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server activates the generative AI and emotion engine. This uses machine learning models and emotion analysis models implemented in programming languages ​​such as Python.

[0636] How generative AI and emotion engines work

[0637] The generative AI analyzes the input goal and performance data and generates a score based on pre-set evaluation criteria. Meanwhile, the emotion engine analyzes the user's facial expressions, voice, and input speed during input to recognize emotional data. This emotional data is incorporated into the evaluation process by the generative AI to generate a more accurate score that takes the user's emotional state into account.

[0638] For example, if the AI ​​is trained with a rating system where "10% increase in sales = 85 points," it will generate a score by incorporating user emotional data. If the emotional data indicates the user's sense of effort or stress level, that information will be reflected in the evaluation.

[0639] Saving and displaying results

[0640] The server stores the generated evaluation results and adjustments based on sentiment data in a database. When saving, it also saves metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data, in addition to the score.

[0641] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points (with sentiment adjustment)" will be displayed.

[0642] Specific example

[0643] For example, the following evaluation process is possible.

[0644] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0645] 2. The device sends this data to the server.

[0646] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0647] 4. The server activates the generative AI and emotion engine, and analyzes the data and user emotion data.

[0648] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the emotion engine recognizes "the user's high stress state" and generates a final score of "75 points" as a correction.

[0649] 6. The server saves an evaluation score of 75 points to the database.

[0650] 7. The server sends the evaluation score to the terminal.

[0651] 8. The device displays the evaluation score to the user.

[0652] Through the above process, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, by incorporating an emotion engine, the user's emotional state is reflected in the evaluation, enabling a more comprehensive and human-centered assessment. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0653] The following describes the processing flow.

[0654] Step 1:

[0655] Users input the target goals and performance data to be evaluated into their terminals. Specifically, users log into the system, access the evaluation form, and input data such as "Project A's goal is a 15% increase in sales" or "Q1 sales increased by 10%."

[0656] Step 2:

[0657] The terminal sends the data entered by the user to the server. After the input is complete, the terminal converts the data to the appropriate format and sends it to the server using an HTTP POST request. At this time, the data is encrypted using SSL / TLS.

[0658] Step 3:

[0659] The server receives data sent from the terminal. The server first checks the completeness and integrity of the received data, and if there are no problems, it saves it to the database. If an error occurs, it returns an error message to the terminal.

[0660] Step 4:

[0661] The server activates the emotion engine. The emotion engine on the server collects data such as the user's facial expressions, voice, and input speed in real time and analyzes the user's emotional state. The analysis results are stored as emotion data.

[0662] Step 5:

[0663] The server launches a generative AI based on the stored data. The server then calls an evaluation machine learning model and starts the evaluation process. Specifically, a model implemented in a programming language such as Python analyzes the target data.

[0664] Step 6:

[0665] Generative AI analyzes data and generates scores based on evaluation criteria. For example, it might generate a score of "85 points" based on an evaluation criterion such as "10% sales growth rate."

[0666] Step 7:

[0667] The server adjusts the score generated based on emotional data. For example, if the user's stress level is high, 5 points are added to the score, and the final score is calculated taking into account the information obtained from the emotional engine.

[0668] Step 8:

[0669] The server saves the generated evaluation results to a database. When saving, in addition to the score, metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data are also saved.

[0670] Step 9:

[0671] The server sends the evaluation results to the terminal. The server returns the evaluation results to the terminal as an HTTP response. The terminal receives this response.

[0672] Step 10:

[0673] The device displays the evaluation results to the user. Specifically, when the user accesses the dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points (with sentiment adjustment)" is displayed. The user can then use this information to take further action or make decisions.

[0674] Through these steps, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, by incorporating an emotion engine, the user's emotional state is reflected in the evaluation, enabling a more comprehensive and human-centered assessment. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0675] (Example 2)

[0676] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0677] Modern evaluation systems suffer from problems with subjectivity and efficiency in the evaluation process. Specifically, traditional evaluation systems rely heavily on the subjectivity of evaluators, often lacking consistency and objectivity in their assessments. Furthermore, proper analysis of input data and rapid provision of results require considerable effort and time, making efficient process management difficult. In addition, because they do not consider the user's emotional state, evaluation results do not accurately reflect the user's actual effort or stress level, which is a significant challenge.

[0678] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for verifying the integrity and consistency of the stored data, means for starting a generative AI and an emotion analysis engine and initiating data analysis, and means for generating a score based on evaluation criteria and reflecting the user's emotion data in the evaluation. This enhances the objectivity and consistency of the evaluation and enables a rapid and effective evaluation process. Furthermore, by considering the user's emotional state, a more human-centered and comprehensive evaluation becomes possible.

[0679] A "user" is an individual or organization that accesses the system and enters goal and performance data.

[0680] A "terminal" is a computer device used by a user to input data and send it to a server.

[0681] A "server" is a device that receives and stores data sent from users and terminals, and performs data analysis by activating generative AI and emotion analysis engines.

[0682] "Target data" refers to data that shows the specific goals and objectives that are being evaluated.

[0683] "Performance data" refers to data that shows the actual results and outcomes in relation to the target.

[0684] "Generative AI" refers to machine learning models used to generate evaluation scores based on input goal and performance data.

[0685] An "emotion analysis engine" is a system that analyzes data such as the user's facial expressions, voice, and input speed, and reflects the user's emotional state in its evaluation.

[0686] "Evaluation criteria" refer to pre-set standards or rules that generative AIs use when generating evaluation scores.

[0687] A "score" is a numerical representation of the evaluation result generated by a generative AI based on evaluation criteria.

[0688] "Metadata" refers to additional information such as the date and time the evaluation results were generated, the evaluation criteria, and sentiment data.

[0689] To implement this invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and sentiment analysis engine collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which the user inputs goal and performance data, which is then analyzed and an evaluation score is generated.

[0690] User-side actions

[0691] Users access the system and input the goals and performance data to be evaluated. For example, a user might use a web browser to access the system's evaluation form and input data such as "Project A Goal: 15% increase in sales" and "Actual: 10% increase in sales in Q1."

[0692] Terminal-side operation

[0693] The terminal sends the data entered by the user to the server. After the user has finished entering the data, the terminal formats this data into JSON format and sends it to the server using an HTTP POST request. SSL / TLS is used to encrypt the data during this process to ensure security.

[0694] Server-side operation

[0695] The server receives and stores data sent from the terminal. First, the server verifies the integrity and validity of the received data. For example, it checks the hash value of the data to ensure it hasn't been tampered with. Once verification is complete, the server saves the data to the database.

[0696] How generative AI and emotion analysis engines work

[0697] After the data has been saved, the server starts the generative AI and sentiment analysis engine. The generative AI uses a Python machine learning model, and the sentiment analysis engine also utilizes Python libraries. These models are then started, and data analysis begins.

[0698] Generative AI analyzes input data based on pre-trained evaluation criteria and generates an evaluation score. For example, an evaluation criterion such as "10% increase in sales = 85 points" is set. On the other hand, the emotion analysis engine generates emotion data by analyzing the user's facial expressions, voice, input speed, etc. In this invention, a more accurate evaluation score is generated by incorporating the user's emotion data into the evaluation.

[0699] Saving and displaying results

[0700] The server stores the generated evaluation results and related metadata (evaluation date and time, evaluation criteria, sentiment data, etc.) in a database. After recording is complete, the server sends the evaluation results to the terminal. The terminal receives the transmitted evaluation results and displays them on the user's screen. For example, when a user accesses the system's dashboard, the results might be displayed as "Q1 Sales Growth Rate Evaluation: 90 points (with sentiment adjustment)".

[0701] Specific example

[0702] The following is an example of a specific evaluation process.

[0703] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department," and "Actual: 5% cost reduction in Q1."

[0704] 2. The device converts this data to JSON format and sends it to the server.

[0705] 3. The server receives the data, verifies its integrity and consistency, and then stores it in the database.

[0706] 4. The server starts the generative AI and emotion analysis engine and begins data analysis.

[0707] 5. The generative AI evaluates "5% cost reduction = 70 points," and the emotion analysis engine recognizes the user's high-stress state, resulting in a final score of "75 points."

[0708] 6. The server saves the evaluation result of 75 points and related metadata to the database.

[0709] 7. The server sends the evaluation results to the terminal.

[0710] 8. The device displays the evaluation score on the user screen, showing "Q1 Cost Reduction Evaluation: 75 points (with sentiment adjustment)".

[0711] Through this process, users can obtain quick and objective evaluation results. The introduction of an emotion analysis engine enables a comprehensive evaluation that reflects the user's emotional state, significantly reducing effort and time.

[0712] Example of a prompt

[0713] For example, here are some examples of prompt statements to input into a generative AI model:

[0714] "Project A's goal was a 15% increase in sales. Sales increased by 10% in the first quarter. Based on user input speed and facial expressions, it appears the user was under high stress during the evaluation process. Please generate the optimal evaluation score based on this information."

[0715] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0716] Step 1:

[0717] The user enters the goals and performance data to be evaluated.

[0718] Specific operation: The user accesses the system's evaluation form using a web browser and enters data such as "Project A's goal: 15% increase in sales" and "Actual results: 10% increase in sales in Q1".

[0719] Input: Target data and performance data.

[0720] Output: Data entered into the evaluation form.

[0721] Step 2:

[0722] The terminal sends the data entered by the user to the server.

[0723] Specific operation: The terminal formats this data into JSON format and sends it to the server via an HTTP POST request. SSL / TLS is used to encrypt the data during this process.

[0724] Input: Target data and performance data formatted in JSON format.

[0725] Output: Encrypted HTTP POST request.

[0726] Step 3:

[0727] The server receives and stores the data sent from the terminal.

[0728] Specific operation: The server first verifies the integrity and consistency of the received data and checks the data's hash value. Once verification is complete, it saves the data to the database.

[0729] Input: Encrypted data.

[0730] Output: Data stored in the database.

[0731] Step 4:

[0732] The server starts up the generative AI and the emotion analysis engine.

[0733] Specific operation: The server runs a generative AI model and sentiment analysis engine via a Python script.

[0734] Input: Saved data.

[0735] Output: An AI model and sentiment analysis engine ready for analysis.

[0736] Step 5:

[0737] Generative AI analyzes input data based on evaluation criteria and generates an evaluation score.

[0738] Specific operation: The generative AI analyzes the data based on pre-trained evaluation criteria. The rule used as a prompt is "10% increase in sales = 85 points".

[0739] Input: Evaluation criteria and saved data.

[0740] Output: Primary evaluation score.

[0741] Step 6:

[0742] The emotion analysis engine analyzes the user's emotional data.

[0743] Specific operation: The emotion analysis engine generates emotion data from the user's facial expressions, voice, input speed, etc.

[0744] Input: User behavior data.

[0745] Output: Sentiment data.

[0746] Step 7:

[0747] The generative AI and the emotion analysis engine work together to generate the final evaluation score.

[0748] Specific operation: The generative AI calculates the final evaluation score by reflecting the emotional data. For example, it corrects an initial evaluation score of 85 points to 90 points.

[0749] Input: Primary evaluation score and sentiment data.

[0750] Output: Final evaluation score.

[0751] Step 8:

[0752] The server stores the generated evaluation results and associated metadata.

[0753] Specific operation: The server stores evaluation results and related metadata (evaluation date and time, evaluation criteria, sentiment data, etc.) in the database.

[0754] Input: Final rating score and metadata.

[0755] Output: Evaluation results and metadata stored in the database.

[0756] Step 9:

[0757] The server sends the evaluation results to the terminal.

[0758] Specific operation: The server sends the evaluation results to the terminal as an HTTP response.

[0759] Input: Final rating score and metadata.

[0760] Output: The evaluation results that were sent.

[0761] Step 10:

[0762] The device displays the evaluation results on the user's screen.

[0763] Specific operation: The terminal analyzes the submitted evaluation results and displays "Q1 Sales Growth Rate Evaluation: 90 points (with sentiment adjustment)" on the user's screen.

[0764] Input: Evaluation results sent from the server.

[0765] Output: The evaluation results displayed to the user.

[0766] (Application Example 2)

[0767] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0768] In modern performance evaluation systems, objectivity and accuracy are challenges when evaluating users' goals and performance data. Furthermore, traditional systems often fail to reflect users' emotional states in evaluations, resulting in evaluations that tend to be purely numerical. This makes fair evaluation and comprehensive, human-centered assessments difficult.

[0769] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for starting a generative AI and an emotion recognition engine and initiating an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, and means for the emotion recognition engine to acquire the user's emotion data and reflect it in the evaluation. This makes it possible to perform a more comprehensive and fair evaluation that takes into account the user's emotion data in addition to their goal and performance data.

[0770] A "user" is an individual or organization that inputs the objectives and performance data to be evaluated.

[0771] A "terminal" is a device that sends data entered by the user to a server and receives and displays evaluation results from the server.

[0772] A "server" is a computing system that receives, stores, and analyzes data sent from a terminal.

[0773] "Generative AI" is artificial intelligence that analyzes goal and performance data entered by the user and generates scores based on pre-trained evaluation criteria.

[0774] An "emotion recognition engine" is an analytical engine that acquires user emotion data and incorporates it into evaluations.

[0775] "Data" refers to information about goals and performance entered by the user.

[0776] A "score" is an evaluation value generated by a generative AI as a result of analyzing data based on evaluation criteria.

[0777] "Emotional data" refers to information about a user's emotional state, obtained from their facial expressions, voice, and other sources.

[0778] "Evaluation criteria" are predetermined standards based on how a generative AI generates a score.

[0779] "Integrity" refers to the check items to ensure that the entered data has not been tampered with.

[0780] "Consistency" refers to the check items that verify whether the entered data conforms to the specified format and content.

[0781] To implement this invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion recognition engine collaborate to perform the evaluation process. The detailed operation of this system is described below.

[0782] User-side actions

[0783] Users access the system and input the objectives and performance data to be evaluated. Specifically, users input data such as "Project A's objective is to reduce the product defect rate by 10%" or "Actual: Material defect rate reduced by 6%" into the terminal. After input, the terminal formats the data into the appropriate format and sends it to the server.

[0784] Terminal-side operation

[0785] The terminal's role is to send data entered by the user to the server. This process uses an HTTP POST request and encrypts the data transmission using SSL / TLS. The transmitted data includes the user's goals and performance data.

[0786] Server-side operation

[0787] The server receives data sent from the terminal and first checks its integrity and consistency. This includes verifying that the data has not been tampered with and that it conforms to the correct format. After verification is complete, the data is saved to the database.

[0788] After saving is complete, the server starts the generative AI and emotion recognition engine. This process uses machine learning models (e.g., linear regression models and neural networks) and emotion analysis models implemented in programming languages ​​such as Python. The generative AI analyzes the input data based on pre-trained evaluation criteria and generates a score. Meanwhile, the emotion recognition engine analyzes emotion data obtained from the user's facial expressions and voice and incorporates it into the evaluation.

[0789] Specific operation of the emotion recognition engine

[0790] The emotion recognition engine uses face recognition (face_recognition) and speech recognition (speech_recognition) libraries to analyze the user's facial expressions and voice data. For example, it uses a camera to capture the user's facial expressions as images and recognize their emotions. It also acquires voice data and performs speech recognition to analyze emotions from the user's voice. The analysis results are reflected in a score as an emotional state such as "positive," "neutral," or "negative."

[0791] Saving and displaying results

[0792] The server stores the generated evaluation results and adjustments based on sentiment data in a database. The data stored includes metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data, in addition to the score. After processing is complete, the server sends the evaluation results to the terminal, and the terminal displays the evaluation results on the user's screen. Specifically, it will display something like "Evaluation result: 75 points (with sentiment adjustment)."

[0793] Specific example

[0794] For example, the following evaluation process is possible:

[0795] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0796] 2. The device sends this data to the server.

[0797] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0798] 4. The server activates the generative AI and emotion recognition engine, and analyzes the data and user emotion data.

[0799] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the emotion recognition engine recognizes "the user's high stress state" and generates a final score of "75 points" as a correction.

[0800] 6. The server saves an evaluation score of 75 points to the database.

[0801] 7. The server sends the evaluation score to the terminal.

[0802] 8. The device displays the evaluation score to the user.

[0803] Example of a prompt

[0804] The following are examples of prompts to input into a generative AI model:

[0805] The goal of Project A is to reduce the product defect rate by 10%.

[0806] Results: Material defect rate reduced by 6%

[0807] Facial expression analysis result: positive

[0808] Voice analysis results: neutral

[0809] In this way, combining generative AI with an emotion recognition engine can improve the objectivity and accuracy of evaluations of user goal and performance data. Furthermore, by incorporating emotional data, a comprehensive evaluation that reflects the user's emotional state becomes possible.

[0810] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0811] Step 1:

[0812] The user inputs the target and performance data to be evaluated into the terminal. Specifically, they enter data such as "Project A's target is a 10% reduction in product defect rate" or "Actual: Material defect rate reduced by 6%" into the designated input fields. This completes the data input process (input: target and performance data, output: formatted data).

[0813] Step 2:

[0814] The terminal sends the goal and performance data entered by the user to the server. The transmission uses an HTTP POST request and SSL / TLS to encrypt the data (input: formatted data, output: data sent to the server).

[0815] Step 3:

[0816] The server receives data sent from the terminal and checks its integrity and consistency. This includes checking for data tampering and verifying format compliance. Once verification is complete, the data is stored in the database (input: sent data, output: verified data).

[0817] Step 4:

[0818] The server activates the generative AI and emotion recognition engine based on the stored data. First, the generative AI analyzes the input data and generates a score based on pre-trained evaluation criteria (input: stored data, output: initial evaluation score).

[0819] Step 5:

[0820] The emotion recognition engine acquires and analyzes the user's emotional data. This process involves using the face recognition library (face_recognition) to acquire facial expression data and the speech recognition library (speech_recognition) to analyze speech data. The analysis results are obtained as emotional states such as "positive," "neutral," and "negative" (input: image and audio data, output: emotional data).

[0821] Step 6:

[0822] The server adjusts the generative AI's score based on the analyzed emotional data. For example, if the generative AI evaluates "5% cost reduction = 70 points" and the emotional recognition engine recognizes "the user is in a high-stress state," it will generate a final score of "75 points" as a correction (input: initial evaluation score, emotional data; output: corrected final score).

[0823] Step 7:

[0824] The server stores the generated evaluation results and adjustments based on sentiment data in a database. The data stored includes metadata such as the evaluation date and time, evaluation criteria, and sentiment data, in addition to the score (input: final evaluation score, output: stored evaluation data).

[0825] Step 8:

[0826] The server sends the evaluation results to the terminal, and the terminal displays the evaluation results to the user. Specifically, it will display something like "Evaluation result: 75 points (with sentiment adjustment)" (Input: saved evaluation data, Output: user's display screen).

[0827] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0828] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0829] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0830] [Third Embodiment]

[0831] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0832] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0833] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0834] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0835] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0836] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0837] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0838] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0839] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0840] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0841] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0842] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0843] To implement this invention, it is necessary to construct a system in which users, terminals, and servers collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0844] User-side actions

[0845] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input specific objectives such as "Project A's objective is a 15% increase in sales" or actual performance data such as "Q1 sales increased by 10%."

[0846] Terminal-side operation

[0847] The terminal's role is to send data entered by the user to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP request. Data transmission is protected using security protocols such as SSL / TLS.

[0848] Server-side operation

[0849] The server's role is to receive and store data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server launches a generative AI. This uses a machine learning model implemented in a programming language such as Python.

[0850] The generative AI analyzes the input target and performance data and generates scores based on pre-set evaluation criteria. For example, if the evaluation criteria for sales growth rate are trained to be "10% increase = 85 points," the AI ​​will generate scores accordingly. The server stores the generated scores in a database.

[0851] Displaying Results

[0852] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" will be displayed.

[0853] Specific example

[0854] For example, the following evaluation process is possible.

[0855] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0856] 2. The device sends this data to the server.

[0857] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0858] 4. The server activates the generative AI and analyzes the data.

[0859] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the server saves this evaluation score to the database.

[0860] 6. The server sends the evaluation score to the terminal.

[0861] 7. The device displays the evaluation score to the user.

[0862] Through the above process, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0863] The following describes the processing flow.

[0864] Step 1:

[0865] Users input the target goals and performance data to be evaluated into their terminal. Specifically, after logging in, users access the evaluation form and input data such as "Project A's goal is a 15% increase in sales" or "Q1 sales increased by 10%."

[0866] Step 2:

[0867] The terminal sends data entered by the user to the server. The terminal converts the data to an appropriate format and sends it to the server using an HTTP POST request or similar method. During this process, SSL / TLS is used to encrypt the data transmission.

[0868] Step 3:

[0869] The server receives data sent from the terminal. The server verifies the integrity and validity of the data and returns an error message to the terminal if there are any errors. If there are no problems, the server saves this data to the database.

[0870] Step 4:

[0871] The server launches a generative AI based on the stored data. Specifically, the server calls a machine learning model implemented in Python or another language and starts the evaluation process.

[0872] Step 5:

[0873] Generative AI analyzes data and generates a score based on evaluation criteria. For example, if the input is "sales growth rate of 10%", a pre-trained model will analyze this and generate a score of "85 points".

[0874] Step 6:

[0875] The server saves the generated evaluation results to a database. When saving, metadata such as the date and time the evaluation was performed and the evaluation criteria are also saved along with the score.

[0876] Step 7:

[0877] The server sends the evaluation results to the terminal. The server returns the evaluation results to the terminal as an HTTP response. The terminal receives this response.

[0878] Step 8:

[0879] The device displays the evaluation results to the user. Specifically, when the user accesses the dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" is displayed. Based on this information, the user can take further actions or make decisions.

[0880] Through these steps, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[0881] (Example 1)

[0882] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0883] Existing evaluation systems often lack objectivity and consistency in their assessments, and subjectivity is particularly likely to creep into the analysis and scoring of evaluation data, making fair evaluation difficult. Furthermore, the evaluation process is often manual, resulting in high time and effort requirements and low efficiency. Additionally, insufficient verification of the integrity and completeness of input data can lead to inaccurate evaluation results.

[0884] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0885] In this invention, the server includes means for the user to input target and performance data to be evaluated, means for the terminal to transmit the input data to the server, means for the server to receive, verify, and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, means for the server to transmit the evaluation results to the terminal, and means for the terminal to display the evaluation results to the user. This ensures objectivity and consistency in evaluation and enables an efficient and accurate evaluation process.

[0886] A "user" refers to an individual or legal entity that is responsible for inputting goal and performance data using the evaluation system.

[0887] "Terminal" refers to a device (e.g., PC, smartphone) that a user uses to access the evaluation system and input and transmit data.

[0888] A "server" refers to a central processing unit that receives data sent from terminals and performs storage and analysis processes.

[0889] "Goal and performance data" refers to numerical or string data entered by the user that indicates specific goals subject to evaluation and their achievement status.

[0890] "Transmission" refers to the act of a terminal transferring data entered by the user to a server.

[0891] "Receiving" refers to the act of a server receiving data sent from a terminal.

[0892] "Verification" refers to the process of confirming the integrity and validity of the data received by the server.

[0893] "Saving" refers to the act of a server recording received data or generated evaluation results in a database.

[0894] "Generative AI" refers to artificial intelligence models trained to perform data analysis and generate evaluation scores.

[0895] The "analysis process" refers to a series of processes by which a generative AI analyzes data and generates a score based on evaluation criteria.

[0896] "Evaluation criteria" refers to pre-set standards used by generative AI when scoring data.

[0897] "Evaluation results" refer to the scores generated by a generative AI based on evaluation criteria after data analysis.

[0898] "Display" refers to the act of showing the evaluation results received by the terminal from the server on the screen in a format that the user can see.

[0899] This invention improves the objectivity and efficiency of evaluation by constructing a system in which users, terminals, and servers collaborate to perform the evaluation process. In this system, users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0900] User-side actions

[0901] Users access the system's evaluation form using their own devices, such as PCs or smartphones. In the evaluation form, users are responsible for entering goal and performance data. For example, a user might enter goal data such as "Project A's goal is a 15% increase in sales" or performance data such as "Q1 sales increased by 10%." The data entered by users plays a crucial role in the system's evaluation process.

[0902] Terminal-side operation

[0903] The terminal's role is to send data entered by the user to the server. Once the user finishes entering data into the evaluation form, the terminal formats this data into an appropriate format (e.g., JSON or XML) and sends it to the server using an HTTP request. During this process, security protocols such as SSL / TLS are used to protect the data during transmission.

[0904] Server-side operation

[0905] The server is the central processing unit that receives data sent from terminals and performs storage and analysis processes. First, the server checks the integrity and consistency of the received data. This verification includes checking the data format and verifying required fields. Once verification is complete, the data is stored in the database. This is done using database operation commands such as SQL.

[0906] Once data is saved, the server launches a generative AI. This generative AI is implemented as a Python script and uses a machine learning model trained for specific data analysis and scoring. The server passes the saved data to the AI ​​model for analysis. The generative AI analyzes the received data and generates a score based on pre-defined evaluation criteria. For example, if the evaluation criterion for sales growth rate is set to "10% increase = 85 points," the AI ​​will calculate the score accordingly.

[0907] The evaluation score generated as a result of the analysis is saved again to the database. After the evaluation score is saved, the server sends the evaluation result to the terminal. The terminal receives this data and displays the evaluation result on the user's screen.

[0908] Specific example

[0909] For example, the following evaluation process is possible:

[0910] 1. The user opens a browser on their device and accesses a specific URL (e.g., https: / / example.com / evaluation). They then enter the following data into the displayed evaluation form: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0911] 2. When the device clicks the "Submit" button, the browser's JavaScript code converts the form data into JSON format and sends a POST request to the server using the HTTPS protocol with SSL / TLS.

[0912] 3. The server receives the request and verifies the format and content of the received data. It checks for format errors and missing required fields.

[0913] 4. The server establishes a database connection and inserts the performance data into the appropriate table in the database using an SQL INSERT statement.

[0914] 5. Once data saving is complete, the server executes a Python script to load a machine learning model (e.g., scikit-learn or TensorFlow). The saved database data is then passed to the model.

[0915] 6. The generating AI inputs data into the model and generates an evaluation score, such as "5% cost reduction = 70 points". The score is stored in temporary memory.

[0916] 7. The server receives the evaluation score and executes an SQL query such as "INSERT INTO scoretable (project, score) VALUES ('project B', 70);" to save the score to the database.

[0917] 8. After the save operation, the server creates an HTTP response containing the evaluation score on the terminal and sends the evaluation result in JSON format in the response body.

[0918] 9. The device receives the HTTP response and parses the JSON response body using JavaScript. The evaluation result is displayed in a UI component (e.g., the evaluation result section of the dashboard), visually informing the user that "Q1 sales growth rate evaluation: 70 points".

[0919] Examples of prompt statements are as follows:

[0920] "Project B's objective is a 10% cost reduction for the department, and the actual result was a 5% cost reduction in Q1. Please generate an evaluation score based on this objective and actual data."

[0921] As described above, the system of the present invention provides a specific form for automating the evaluation process and improving the objectivity and efficiency of the evaluation.

[0922] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0923] Step 1:

[0924] The user enters the goals and performance data to be evaluated.

[0925] Input: Data entered by the user in the device evaluation form (e.g., "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1")

[0926] Action: The user opens a browser and accesses a specific URL. The user enters goal and performance data into an evaluation form and clicks the "Submit" button.

[0927] Output: The input data is temporarily stored on the terminal.

[0928] Step 2:

[0929] The terminal sends the entered data to the server.

[0930] Input: Data entered in the evaluation form

[0931] Operation: The device uses the browser's JavaScript code to convert the form data into JSON format. The converted data is sent to the server using the HTTPS protocol with SSL / TLS.

[0932] Output: JSON data sent to the server

[0933] Step 3:

[0934] The server receives, verifies, and stores the data.

[0935] Input: JSON data sent from the device

[0936] Operation: The server receives an HTTP request and checks the format of the received data and verifies required fields. Once verification is complete, the data is saved to the database. The data is then inserted into the appropriate table in the database using an SQL INSERT statement.

[0937] Output: Evaluation data stored in the database

[0938] Step 4:

[0939] The server activates a generative AI based on the stored data and begins the analysis process.

[0940] Input: Evaluation data stored in the database

[0941] Operation: The server executes a Python script and loads a machine learning model (e.g., scikit-learn or TensorFlow). It then passes data from a stored database to the model.

[0942] Output: Evaluation data received by the generative AI

[0943] Step 5:

[0944] Generative AI analyzes the data and generates a score based on evaluation criteria.

[0945] Input: Evaluation data passed to the generative AI

[0946] Operation: The generative AI analyzes data based on pre-defined evaluation criteria. For example, it might evaluate "5% cost reduction = 70 points." The score is stored in temporary memory.

[0947] Output: Generated evaluation score

[0948] Step 6:

[0949] The server saves the generated evaluation results.

[0950] Input: Evaluation score generated by a generative AI

[0951] Operation: The server receives the evaluation score and saves it back to the database. It executes an SQL query such as "INSERT INTO scoretable (project, score) VALUES ('project B', 70);".

[0952] Output: Evaluation scores stored in the database

[0953] Step 7:

[0954] The server sends the evaluation results to the terminal.

[0955] Input: Evaluation score stored in the database

[0956] Operation: The server generates an evaluation score as an HTTP response and sends the evaluation result to the terminal in JSON format.

[0957] Output: JSON data of the evaluation results sent to the terminal.

[0958] Step 8:

[0959] The device displays the evaluation results to the user.

[0960] Input: JSON data of evaluation results sent from the server

[0961] Operation: The device receives an HTTP response and parses the JSON response body using JavaScript code. The evaluation result is displayed in a UI component (e.g., the evaluation results section of the dashboard), visually informing the user of "Q1 sales growth rate evaluation: 70 points".

[0962] Output: Evaluation results displayed on the user's screen

[0963] The above describes the specific processing steps in the system of the present invention. This ensures objectivity and efficiency in evaluation, and realizes an accurate and rapid evaluation process.

[0964] (Application Example 1)

[0965] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0966] Traditional personnel evaluation and performance evaluation systems lacked objectivity and efficiency, often involving subjective judgments, leading to unfair evaluation results. Furthermore, the evaluation process was time-consuming and labor-intensive. In addition, performance evaluation in logistics center management was highly subjective, making efficient improvement measures difficult.

[0967] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0968] In this invention, the server includes means for the user to input target and performance data to be evaluated, means for the terminal to transmit the input data to the server, means for the server to receive and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, means for the terminal to display the evaluation results to the user, and means for logging, and means for generating an evaluation score using a generative AI that calculates performance based on the input data of targets and performance. This improves the objectivity and efficiency of the evaluation, enabling rapid and fair performance evaluation of the logistics center.

[0969] A "user" is the entity that accesses the system and inputs goal and performance data.

[0970] A "terminal" is a computer device used to send data entered by a user to a server.

[0971] A "server" is a computer device that stores data received from terminals, initiates the analysis process, generates evaluation results, and stores them.

[0972] "Generative AI" refers to artificial intelligence models that analyze input data and generate scores based on evaluation criteria.

[0973] "Evaluation criteria" refer to pre-set rules or standards that a generative AI follows when generating a score.

[0974] A "score" is an evaluation value generated by a generative AI based on evaluation criteria.

[0975] A "logging means" is a means that has the function of recording and saving operation logs such as evaluation processes and data reception and storage.

[0976] "Target and performance data" refers to the specific numerical targets and performance data entered by the user for evaluation.

[0977] "Results" refer to data on the actual outcomes achieved in relation to the goals.

[0978] "Data integrity" refers to the state in which received data remains accurate and unchanged from what was intended by the sender.

[0979] "Consistency" refers to a state where received data is consistent with other data and existing systems, and free from contradictions.

[0980] To implement this invention, it is necessary to construct a system in which users, terminals, and servers collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[0981] User-side actions

[0982] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input specific objectives such as "Project A's objective is a 15% increase in sales" or actual performance data such as "Q1 sales increased by 10%."

[0983] Terminal-side operation

[0984] The terminal's role is to send data entered by the user to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP request. Data transmission is protected using security protocols such as SSL / TLS.

[0985] Server-side operation

[0986] The server's role is to receive and store data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server launches a generative AI. This uses a machine learning model implemented in a programming language such as Python.

[0987] The generative AI analyzes the input target and performance data and generates scores based on pre-set evaluation criteria. For example, if the evaluation criteria for sales growth rate are trained to be "10% increase = 85 points," the AI ​​will generate scores accordingly. The server stores the generated scores in a database.

[0988] Displaying Results

[0989] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" will be displayed.

[0990] A series of specific examples

[0991] For example, the following evaluation process is possible.

[0992] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[0993] 2. The device sends this data to the server.

[0994] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[0995] 4. The server activates the generative AI and analyzes the data.

[0996] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the server saves this evaluation score to the database.

[0997] 6. The server sends the evaluation score to the terminal.

[0998] 7. The device displays the evaluation score to the user.

[0999] Examples of prompts to input into a generative AI model

[1000] "Employee A's Q1 target was a 15% reduction in inventory. Their actual result was a 10% reduction. Please calculate their performance score."

[1001] Hardware and software to be used

[1002] Server: Uses Flask and SQLite for data processing and analysis.

[1003] Generative AI: Python and scikit-learn are used for score calculation.

[1004] Data protection: Uses SSL / TLS protocol.

[1005] Frontend: Utilizes a web interface optimized for smartphones.

[1006] As a result, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[1007] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1008] Step 1: The user enters goal and performance data.

[1009] ---

[1010] Users access the system's evaluation form using their own devices and enter the evaluation target (e.g., "15% increase in sales") and performance data (e.g., "Q1 sales increased by 10%"). The entered data is saved on the device.

[1011] Step 2: The device sends data to the server.

[1012] ---

[1013] The terminal formats the data entered by the user into the appropriate format and sends it to the server using an HTTP request. SSL / TLS protocol is used to protect the data. Input data includes numerical data for targets and actual results. The output is the data sent to the server.

[1014] Step 3: The server receives and stores the data.

[1015] ---

[1016] The server receives data sent from the terminal. It then checks the integrity and validity of the received data. Once the data is deemed acceptable, it saves it to a database (such as SQLite). In this case, the input is the data sent from the terminal, and the output is the data stored in the database.

[1017] Step 4: The server starts the generative AI model and begins the analysis process.

[1018] ---

[1019] The server launches a generative AI model using data stored in the database. This AI model is implemented using Python or scikit-learn. The generative AI analyzes the data based on pre-defined evaluation criteria and generates a score. The input is stored target and performance data, and the output is the generated evaluation score.

[1020] Step 5: The server saves the generated evaluation score.

[1021] ---

[1022] The evaluation score generated by the generative AI is then saved again to the database by the server. The input is the score generated by the generative AI, and the output is the score saved in the database.

[1023] Step 6: The server sends the evaluation results to the terminal.

[1024] ---

[1025] The server sends the generated evaluation score to the terminal. It returns data containing the evaluation score in an HTTP response. The input is the score stored in the database, and the output is the score data sent to the terminal.

[1026] Step 7: The device displays the evaluation results to the user.

[1027] ---

[1028] The terminal displays the evaluation results received from the server on the user's screen. Specifically, evaluation results such as "Q1 Sales Growth Rate Evaluation: 85 points" can be seen through the dashboard function. The input is the score data sent from the server, and the output is the evaluation result displayed on the user's screen.

[1029] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1030] To implement the present invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion engine collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which the user inputs goal and performance data, and the generative AI and emotion engine analyze this data to generate an evaluation score.

[1031] User-side actions

[1032] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input data such as "Project A's objective is a 15% increase in sales" or "Q1 sales increased by 10%."

[1033] Terminal-side operation

[1034] The terminal's role is to send user-entered data to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP POST request. SSL / TLS is used to encrypt the data transmission during this process.

[1035] Server-side operation

[1036] The server is responsible for receiving and storing data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server activates the generative AI and emotion engine. This uses machine learning models and emotion analysis models implemented in programming languages ​​such as Python.

[1037] How generative AI and emotion engines work

[1038] The generative AI analyzes the input goal and performance data and generates a score based on pre-set evaluation criteria. Meanwhile, the emotion engine analyzes the user's facial expressions, voice, and input speed during input to recognize emotional data. This emotional data is incorporated into the evaluation process by the generative AI to generate a more accurate score that takes the user's emotional state into account.

[1039] For example, if the AI ​​is trained with a rating system where "10% increase in sales = 85 points," it will generate a score by incorporating user emotional data. If the emotional data indicates the user's sense of effort or stress level, that information will be reflected in the evaluation.

[1040] Saving and displaying results

[1041] The server stores the generated evaluation results and adjustments based on sentiment data in a database. When saving, it also saves metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data, in addition to the score.

[1042] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points (with sentiment adjustment)" will be displayed.

[1043] Specific example

[1044] For example, the following evaluation process is possible.

[1045] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[1046] 2. The device sends this data to the server.

[1047] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[1048] 4. The server activates the generative AI and emotion engine, and analyzes the data and user emotion data.

[1049] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the emotion engine recognizes "the user's high stress state" and generates a final score of "75 points" as a correction.

[1050] 6. The server saves an evaluation score of 75 points to the database.

[1051] 7. The server sends the evaluation score to the terminal.

[1052] 8. The device displays the evaluation score to the user.

[1053] Through the above process, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, by incorporating an emotion engine, the user's emotional state is reflected in the evaluation, enabling a more comprehensive and human-centered assessment. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[1054] The following describes the processing flow.

[1055] Step 1:

[1056] Users input the target goals and performance data to be evaluated into their terminals. Specifically, users log into the system, access the evaluation form, and input data such as "Project A's goal is a 15% increase in sales" or "Q1 sales increased by 10%."

[1057] Step 2:

[1058] The terminal sends the data entered by the user to the server. After the input is complete, the terminal converts the data to the appropriate format and sends it to the server using an HTTP POST request. At this time, the data is encrypted using SSL / TLS.

[1059] Step 3:

[1060] The server receives data sent from the terminal. The server first checks the completeness and integrity of the received data, and if there are no problems, it saves it to the database. If an error occurs, it returns an error message to the terminal.

[1061] Step 4:

[1062] The server activates the emotion engine. The emotion engine on the server collects data such as the user's facial expressions, voice, and input speed in real time and analyzes the user's emotional state. The analysis results are stored as emotion data.

[1063] Step 5:

[1064] The server launches a generative AI based on the stored data. The server then calls an evaluation machine learning model and starts the evaluation process. Specifically, a model implemented in a programming language such as Python analyzes the target data.

[1065] Step 6:

[1066] Generative AI analyzes data and generates scores based on evaluation criteria. For example, it might generate a score of "85 points" based on an evaluation criterion such as "10% sales growth rate."

[1067] Step 7:

[1068] The server adjusts the score generated based on emotional data. For example, if the user's stress level is high, 5 points are added to the score, and the final score is calculated taking into account the information obtained from the emotional engine.

[1069] Step 8:

[1070] The server saves the generated evaluation results to a database. When saving, in addition to the score, metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data are also saved.

[1071] Step 9:

[1072] The server sends the evaluation results to the terminal. The server returns the evaluation results to the terminal as an HTTP response. The terminal receives this response.

[1073] Step 10:

[1074] The device displays the evaluation results to the user. Specifically, when the user accesses the dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points (with sentiment adjustment)" is displayed. The user can then use this information to take further action or make decisions.

[1075] Through these steps, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, by incorporating an emotion engine, the user's emotional state is reflected in the evaluation, enabling a more comprehensive and human-centered assessment. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[1076] (Example 2)

[1077] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1078] Modern evaluation systems suffer from problems with subjectivity and efficiency in the evaluation process. Specifically, traditional evaluation systems rely heavily on the subjectivity of evaluators, often lacking consistency and objectivity in their assessments. Furthermore, proper analysis of input data and rapid provision of results require considerable effort and time, making efficient process management difficult. In addition, because they do not consider the user's emotional state, evaluation results do not accurately reflect the user's actual effort or stress level, which is a significant challenge.

[1079] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for verifying the integrity and consistency of the stored data, means for starting a generative AI and an emotion analysis engine and initiating data analysis, and means for generating a score based on evaluation criteria and reflecting the user's emotion data in the evaluation. This enhances the objectivity and consistency of the evaluation and enables a rapid and effective evaluation process. Furthermore, by considering the user's emotional state, a more human-centered and comprehensive evaluation becomes possible.

[1080] A "user" is an individual or organization that accesses the system and enters goal and performance data.

[1081] A "terminal" is a computer device used by a user to input data and send it to a server.

[1082] A "server" is a device that receives and stores data sent from users and terminals, and performs data analysis by activating generative AI and emotion analysis engines.

[1083] "Target data" refers to data that shows the specific goals and objectives that are being evaluated.

[1084] "Performance data" refers to data that shows the actual results and outcomes in relation to the target.

[1085] "Generative AI" refers to machine learning models used to generate evaluation scores based on input goal and performance data.

[1086] An "emotion analysis engine" is a system that analyzes data such as the user's facial expressions, voice, and input speed, and reflects the user's emotional state in its evaluation.

[1087] "Evaluation criteria" refer to pre-set standards or rules that generative AIs use when generating evaluation scores.

[1088] A "score" is a numerical representation of the evaluation result generated by a generative AI based on evaluation criteria.

[1089] "Metadata" refers to additional information such as the date and time the evaluation results were generated, the evaluation criteria, and sentiment data.

[1090] To implement this invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and sentiment analysis engine collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which the user inputs goal and performance data, which is then analyzed and an evaluation score is generated.

[1091] User-side actions

[1092] Users access the system and input the goals and performance data to be evaluated. For example, a user might use a web browser to access the system's evaluation form and input data such as "Project A Goal: 15% increase in sales" and "Actual: 10% increase in sales in Q1."

[1093] Terminal-side operation

[1094] The terminal sends the data entered by the user to the server. After the user has finished entering the data, the terminal formats this data into JSON format and sends it to the server using an HTTP POST request. SSL / TLS is used to encrypt the data during this process to ensure security.

[1095] Server-side operation

[1096] The server receives and stores data sent from the terminal. First, the server verifies the integrity and validity of the received data. For example, it checks the hash value of the data to ensure it hasn't been tampered with. Once verification is complete, the server saves the data to the database.

[1097] How generative AI and emotion analysis engines work

[1098] After the data has been saved, the server starts the generative AI and sentiment analysis engine. The generative AI uses a Python machine learning model, and the sentiment analysis engine also utilizes Python libraries. These models are then started, and data analysis begins.

[1099] Generative AI analyzes input data based on pre-trained evaluation criteria and generates an evaluation score. For example, an evaluation criterion such as "10% increase in sales = 85 points" is set. On the other hand, the emotion analysis engine generates emotion data by analyzing the user's facial expressions, voice, input speed, etc. In this invention, a more accurate evaluation score is generated by incorporating the user's emotion data into the evaluation.

[1100] Saving and displaying results

[1101] The server stores the generated evaluation results and related metadata (evaluation date and time, evaluation criteria, sentiment data, etc.) in a database. After recording is complete, the server sends the evaluation results to the terminal. The terminal receives the transmitted evaluation results and displays them on the user's screen. For example, when a user accesses the system's dashboard, the results might be displayed as "Q1 Sales Growth Rate Evaluation: 90 points (with sentiment adjustment)".

[1102] Specific example

[1103] The following is an example of a specific evaluation process.

[1104] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department," and "Actual: 5% cost reduction in Q1."

[1105] 2. The device converts this data to JSON format and sends it to the server.

[1106] 3. The server receives the data, verifies its integrity and consistency, and then stores it in the database.

[1107] 4. The server starts the generative AI and emotion analysis engine and begins data analysis.

[1108] 5. The generative AI evaluates "5% cost reduction = 70 points," and the emotion analysis engine recognizes the user's high-stress state, resulting in a final score of "75 points."

[1109] 6. The server saves the evaluation result of 75 points and related metadata to the database.

[1110] 7. The server sends the evaluation results to the terminal.

[1111] 8. The device displays the evaluation score on the user screen, showing "Q1 Cost Reduction Evaluation: 75 points (with sentiment adjustment)".

[1112] Through this process, users can obtain quick and objective evaluation results. The introduction of an emotion analysis engine enables a comprehensive evaluation that reflects the user's emotional state, significantly reducing effort and time.

[1113] Example of a prompt

[1114] For example, here are some examples of prompt statements to input into a generative AI model:

[1115] "Project A's goal was a 15% increase in sales. Sales increased by 10% in the first quarter. Based on user input speed and facial expressions, it appears the user was under high stress during the evaluation process. Please generate the optimal evaluation score based on this information."

[1116] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1117] Step 1:

[1118] The user enters the goals and performance data to be evaluated.

[1119] Specific operation: The user accesses the system's evaluation form using a web browser and enters data such as "Project A's goal: 15% increase in sales" and "Actual results: 10% increase in sales in Q1".

[1120] Input: Target data and performance data.

[1121] Output: Data entered into the evaluation form.

[1122] Step 2:

[1123] The terminal sends the data entered by the user to the server.

[1124] Specific operation: The terminal formats this data into JSON format and sends it to the server via an HTTP POST request. SSL / TLS is used to encrypt the data during this process.

[1125] Input: Target data and performance data formatted in JSON format.

[1126] Output: Encrypted HTTP POST request.

[1127] Step 3:

[1128] The server receives and stores the data sent from the terminal.

[1129] Specific operation: The server first verifies the integrity and consistency of the received data and checks the data's hash value. Once verification is complete, it saves the data to the database.

[1130] Input: Encrypted data.

[1131] Output: Data stored in the database.

[1132] Step 4:

[1133] The server starts up the generative AI and the emotion analysis engine.

[1134] Specific operation: The server runs a generative AI model and sentiment analysis engine via a Python script.

[1135] Input: Saved data.

[1136] Output: An AI model and sentiment analysis engine ready for analysis.

[1137] Step 5:

[1138] Generative AI analyzes input data based on evaluation criteria and generates an evaluation score.

[1139] Specific operation: The generative AI analyzes the data based on pre-trained evaluation criteria. The rule used as a prompt is "10% increase in sales = 85 points".

[1140] Input: Evaluation criteria and saved data.

[1141] Output: Primary evaluation score.

[1142] Step 6:

[1143] The emotion analysis engine analyzes the user's emotional data.

[1144] Specific operation: The emotion analysis engine generates emotion data from the user's facial expressions, voice, input speed, etc.

[1145] Input: User behavior data.

[1146] Output: Sentiment data.

[1147] Step 7:

[1148] The generative AI and the emotion analysis engine work together to generate the final evaluation score.

[1149] Specific operation: The generative AI calculates the final evaluation score by reflecting the emotional data. For example, it corrects an initial evaluation score of 85 points to 90 points.

[1150] Input: Primary evaluation score and sentiment data.

[1151] Output: Final evaluation score.

[1152] Step 8:

[1153] The server stores the generated evaluation results and associated metadata.

[1154] Specific operation: The server stores evaluation results and related metadata (evaluation date and time, evaluation criteria, sentiment data, etc.) in the database.

[1155] Input: Final rating score and metadata.

[1156] Output: Evaluation results and metadata stored in the database.

[1157] Step 9:

[1158] The server sends the evaluation results to the terminal.

[1159] Specific operation: The server sends the evaluation results to the terminal as an HTTP response.

[1160] Input: Final rating score and metadata.

[1161] Output: The evaluation results that were sent.

[1162] Step 10:

[1163] The device displays the evaluation results on the user's screen.

[1164] Specific operation: The terminal analyzes the submitted evaluation results and displays "Q1 Sales Growth Rate Evaluation: 90 points (with sentiment adjustment)" on the user's screen.

[1165] Input: Evaluation results sent from the server.

[1166] Output: The evaluation results displayed to the user.

[1167] (Application Example 2)

[1168] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1169] In modern performance evaluation systems, objectivity and accuracy are challenges when evaluating users' goals and performance data. Furthermore, traditional systems often fail to reflect users' emotional states in evaluations, resulting in evaluations that tend to be purely numerical. This makes fair evaluation and comprehensive, human-centered assessments difficult.

[1170] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for starting a generative AI and an emotion recognition engine and initiating an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, and means for the emotion recognition engine to acquire the user's emotion data and reflect it in the evaluation. This makes it possible to perform a more comprehensive and fair evaluation that takes into account the user's emotion data in addition to their goal and performance data.

[1171] A "user" is an individual or organization that inputs the objectives and performance data to be evaluated.

[1172] A "terminal" is a device that sends data entered by the user to a server and receives and displays evaluation results from the server.

[1173] A "server" is a computing system that receives, stores, and analyzes data sent from a terminal.

[1174] "Generative AI" is artificial intelligence that analyzes goal and performance data entered by the user and generates scores based on pre-trained evaluation criteria.

[1175] An "emotion recognition engine" is an analytical engine that acquires user emotion data and incorporates it into evaluations.

[1176] "Data" refers to information about goals and performance entered by the user.

[1177] A "score" is an evaluation value generated by a generative AI as a result of analyzing data based on evaluation criteria.

[1178] "Emotional data" refers to information about a user's emotional state, obtained from their facial expressions, voice, and other sources.

[1179] "Evaluation criteria" are predetermined standards based on how a generative AI generates a score.

[1180] "Integrity" refers to the check items to ensure that the entered data has not been tampered with.

[1181] "Consistency" refers to the check items that verify whether the entered data conforms to the specified format and content.

[1182] To implement this invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion recognition engine collaborate to perform the evaluation process. The detailed operation of this system is described below.

[1183] User-side actions

[1184] Users access the system and input the objectives and performance data to be evaluated. Specifically, users input data such as "Project A's objective is to reduce the product defect rate by 10%" or "Actual: Material defect rate reduced by 6%" into the terminal. After input, the terminal formats the data into the appropriate format and sends it to the server.

[1185] Terminal-side operation

[1186] The terminal's role is to send data entered by the user to the server. This process uses an HTTP POST request and encrypts the data transmission using SSL / TLS. The transmitted data includes the user's goals and performance data.

[1187] Server-side operation

[1188] The server receives data sent from the terminal and first checks its integrity and consistency. This includes verifying that the data has not been tampered with and that it conforms to the correct format. After verification is complete, the data is saved to the database.

[1189] After saving is complete, the server starts the generative AI and emotion recognition engine. This process uses machine learning models (e.g., linear regression models and neural networks) and emotion analysis models implemented in programming languages ​​such as Python. The generative AI analyzes the input data based on pre-trained evaluation criteria and generates a score. Meanwhile, the emotion recognition engine analyzes emotion data obtained from the user's facial expressions and voice and incorporates it into the evaluation.

[1190] Specific operation of the emotion recognition engine

[1191] The emotion recognition engine uses face recognition (face_recognition) and speech recognition (speech_recognition) libraries to analyze the user's facial expressions and voice data. For example, it uses a camera to capture the user's facial expressions as images and recognize their emotions. It also acquires voice data and performs speech recognition to analyze emotions from the user's voice. The analysis results are reflected in a score as an emotional state such as "positive," "neutral," or "negative."

[1192] Saving and displaying results

[1193] The server stores the generated evaluation results and adjustments based on sentiment data in a database. The data stored includes metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data, in addition to the score. After processing is complete, the server sends the evaluation results to the terminal, and the terminal displays the evaluation results on the user's screen. Specifically, it will display something like "Evaluation result: 75 points (with sentiment adjustment)."

[1194] Specific example

[1195] For example, the following evaluation process is possible:

[1196] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[1197] 2. The device sends this data to the server.

[1198] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[1199] 4. The server activates the generative AI and emotion recognition engine, and analyzes the data and user emotion data.

[1200] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the emotion recognition engine recognizes "the user's high stress state" and generates a final score of "75 points" as a correction.

[1201] 6. The server saves an evaluation score of 75 points to the database.

[1202] 7. The server sends the evaluation score to the terminal.

[1203] 8. The device displays the evaluation score to the user.

[1204] Example of a prompt

[1205] The following are examples of prompts to input into a generative AI model:

[1206] The goal of Project A is to reduce the product defect rate by 10%.

[1207] Results: Material defect rate reduced by 6%

[1208] Facial expression analysis result: positive

[1209] Voice analysis results: neutral

[1210] In this way, combining generative AI with an emotion recognition engine can improve the objectivity and accuracy of evaluations of user goal and performance data. Furthermore, by incorporating emotional data, a comprehensive evaluation that reflects the user's emotional state becomes possible.

[1211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1212] Step 1:

[1213] The user inputs the target and performance data to be evaluated into the terminal. Specifically, they enter data such as "Project A's target is a 10% reduction in product defect rate" or "Actual: Material defect rate reduced by 6%" into the designated input fields. This completes the data input process (input: target and performance data, output: formatted data).

[1214] Step 2:

[1215] The terminal sends the goal and performance data entered by the user to the server. The transmission uses an HTTP POST request and SSL / TLS to encrypt the data (input: formatted data, output: data sent to the server).

[1216] Step 3:

[1217] The server receives data sent from the terminal and checks its integrity and consistency. This includes checking for data tampering and verifying format compliance. Once verification is complete, the data is stored in the database (input: sent data, output: verified data).

[1218] Step 4:

[1219] The server activates the generative AI and emotion recognition engine based on the stored data. First, the generative AI analyzes the input data and generates a score based on pre-trained evaluation criteria (input: stored data, output: initial evaluation score).

[1220] Step 5:

[1221] The emotion recognition engine acquires and analyzes the user's emotional data. This process involves using the face recognition library (face_recognition) to acquire facial expression data and the speech recognition library (speech_recognition) to analyze speech data. The analysis results are obtained as emotional states such as "positive," "neutral," and "negative" (input: image and audio data, output: emotional data).

[1222] Step 6:

[1223] The server adjusts the generative AI's score based on the analyzed emotional data. For example, if the generative AI evaluates "5% cost reduction = 70 points" and the emotional recognition engine recognizes "the user is in a high-stress state," it will generate a final score of "75 points" as a correction (input: initial evaluation score, emotional data; output: corrected final score).

[1224] Step 7:

[1225] The server stores the generated evaluation results and adjustments based on sentiment data in a database. The data stored includes metadata such as the evaluation date and time, evaluation criteria, and sentiment data, in addition to the score (input: final evaluation score, output: stored evaluation data).

[1226] Step 8:

[1227] The server sends the evaluation results to the terminal, and the terminal displays the evaluation results to the user. Specifically, it will display something like "Evaluation result: 75 points (with sentiment adjustment)" (Input: saved evaluation data, Output: user's display screen).

[1228] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1229] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1230] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1231] [Fourth Embodiment]

[1232] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1233] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1234] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1235] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1236] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1237] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1238] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1239] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1240] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1241] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1242] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1243] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1244] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1245] To implement this invention, it is necessary to construct a system in which users, terminals, and servers collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[1246] User-side actions

[1247] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input specific objectives such as "Project A's objective is a 15% increase in sales" or actual performance data such as "Q1 sales increased by 10%."

[1248] Terminal-side operation

[1249] The terminal's role is to send data entered by the user to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP request. Data transmission is protected using security protocols such as SSL / TLS.

[1250] Server-side operation

[1251] The server's role is to receive and store data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server launches a generative AI. This uses a machine learning model implemented in a programming language such as Python.

[1252] The generative AI analyzes the input target and performance data and generates scores based on pre-set evaluation criteria. For example, if the evaluation criteria for sales growth rate are trained to be "10% increase = 85 points," the AI ​​will generate scores accordingly. The server stores the generated scores in a database.

[1253] Displaying Results

[1254] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" will be displayed.

[1255] Specific example

[1256] For example, the following evaluation process is possible.

[1257] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[1258] 2. The device sends this data to the server.

[1259] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[1260] 4. The server activates the generative AI and analyzes the data.

[1261] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the server saves this evaluation score to the database.

[1262] 6. The server sends the evaluation score to the terminal.

[1263] 7. The device displays the evaluation score to the user.

[1264] Through the above process, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[1265] The following describes the processing flow.

[1266] Step 1:

[1267] Users input the target goals and performance data to be evaluated into their terminal. Specifically, after logging in, users access the evaluation form and input data such as "Project A's goal is a 15% increase in sales" or "Q1 sales increased by 10%."

[1268] Step 2:

[1269] The terminal sends data entered by the user to the server. The terminal converts the data to an appropriate format and sends it to the server using an HTTP POST request or similar method. During this process, SSL / TLS is used to encrypt the data transmission.

[1270] Step 3:

[1271] The server receives data sent from the terminal. The server verifies the integrity and validity of the data and returns an error message to the terminal if there are any errors. If there are no problems, the server saves this data to the database.

[1272] Step 4:

[1273] The server launches a generative AI based on the stored data. Specifically, the server calls a machine learning model implemented in Python or another language and starts the evaluation process.

[1274] Step 5:

[1275] Generative AI analyzes data and generates a score based on evaluation criteria. For example, if the input is "sales growth rate of 10%", a pre-trained model will analyze this and generate a score of "85 points".

[1276] Step 6:

[1277] The server saves the generated evaluation results to a database. When saving, metadata such as the date and time the evaluation was performed and the evaluation criteria are also saved along with the score.

[1278] Step 7:

[1279] The server sends the evaluation results to the terminal. The server returns the evaluation results to the terminal as an HTTP response. The terminal receives this response.

[1280] Step 8:

[1281] The device displays the evaluation results to the user. Specifically, when the user accesses the dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" is displayed. Based on this information, the user can take further actions or make decisions.

[1282] Through these steps, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[1283] (Example 1)

[1284] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1285] Existing evaluation systems often lack objectivity and consistency in their assessments, and subjectivity is particularly likely to creep into the analysis and scoring of evaluation data, making fair evaluation difficult. Furthermore, the evaluation process is often manual, resulting in high time and effort requirements and low efficiency. Additionally, insufficient verification of the integrity and completeness of input data can lead to inaccurate evaluation results.

[1286] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1287] In this invention, the server includes means for the user to input target and performance data to be evaluated, means for the terminal to transmit the input data to the server, means for the server to receive, verify, and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, means for the server to transmit the evaluation results to the terminal, and means for the terminal to display the evaluation results to the user. This ensures objectivity and consistency in evaluation and enables an efficient and accurate evaluation process.

[1288] A "user" refers to an individual or legal entity that is responsible for inputting goal and performance data using the evaluation system.

[1289] "Terminal" refers to a device (e.g., PC, smartphone) that a user uses to access the evaluation system and input and transmit data.

[1290] A "server" refers to a central processing unit that receives data sent from terminals and performs storage and analysis processes.

[1291] "Goal and performance data" refers to numerical or string data entered by the user that indicates specific goals subject to evaluation and their achievement status.

[1292] "Transmission" refers to the act of a terminal transferring data entered by the user to a server.

[1293] "Receiving" refers to the act of a server receiving data sent from a terminal.

[1294] "Verification" refers to the process of confirming the integrity and validity of the data received by the server.

[1295] "Saving" refers to the act of a server recording received data or generated evaluation results in a database.

[1296] "Generative AI" refers to artificial intelligence models trained to perform data analysis and generate evaluation scores.

[1297] The "analysis process" refers to a series of processes by which a generative AI analyzes data and generates a score based on evaluation criteria.

[1298] "Evaluation criteria" refers to pre-set standards used by generative AI when scoring data.

[1299] "Evaluation results" refer to the scores generated by a generative AI based on evaluation criteria after data analysis.

[1300] "Display" refers to the act of showing the evaluation results received by the terminal from the server on the screen in a format that the user can see.

[1301] This invention improves the objectivity and efficiency of evaluation by constructing a system in which users, terminals, and servers collaborate to perform the evaluation process. In this system, users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[1302] User-side actions

[1303] Users access the system's evaluation form using their own devices, such as PCs or smartphones. In the evaluation form, users are responsible for entering goal and performance data. For example, a user might enter goal data such as "Project A's goal is a 15% increase in sales" or performance data such as "Q1 sales increased by 10%." The data entered by users plays a crucial role in the system's evaluation process.

[1304] Terminal-side operation

[1305] The terminal's role is to send data entered by the user to the server. Once the user finishes entering data into the evaluation form, the terminal formats this data into an appropriate format (e.g., JSON or XML) and sends it to the server using an HTTP request. During this process, security protocols such as SSL / TLS are used to protect the data during transmission.

[1306] Server-side operation

[1307] The server is the central processing unit that receives data sent from terminals and performs storage and analysis processes. First, the server checks the integrity and consistency of the received data. This verification includes checking the data format and verifying required fields. Once verification is complete, the data is stored in the database. This is done using database operation commands such as SQL.

[1308] Once data is saved, the server launches a generative AI. This generative AI is implemented as a Python script and uses a machine learning model trained for specific data analysis and scoring. The server passes the saved data to the AI ​​model for analysis. The generative AI analyzes the received data and generates a score based on pre-defined evaluation criteria. For example, if the evaluation criterion for sales growth rate is set to "10% increase = 85 points," the AI ​​will calculate the score accordingly.

[1309] The evaluation score generated as a result of the analysis is saved again to the database. After the evaluation score is saved, the server sends the evaluation result to the terminal. The terminal receives this data and displays the evaluation result on the user's screen.

[1310] Specific example

[1311] For example, the following evaluation process is possible:

[1312] 1. The user opens a browser on their device and accesses a specific URL (e.g., https: / / example.com / evaluation). They then enter the following data into the displayed evaluation form: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[1313] 2. When the device clicks the "Submit" button, the browser's JavaScript code converts the form data into JSON format and sends a POST request to the server using the HTTPS protocol with SSL / TLS.

[1314] 3. The server receives the request and verifies the format and content of the received data. It checks for format errors and missing required fields.

[1315] 4. The server establishes a database connection and inserts the performance data into the appropriate table in the database using an SQL INSERT statement.

[1316] 5. Once data saving is complete, the server executes a Python script to load a machine learning model (e.g., scikit-learn or TensorFlow). The saved database data is then passed to the model.

[1317] 6. The generating AI inputs data into the model and generates an evaluation score, such as "5% cost reduction = 70 points". The score is stored in temporary memory.

[1318] 7. The server receives the evaluation score and executes an SQL query such as "INSERT INTO scoretable (project, score) VALUES ('project B', 70);" to save the score to the database.

[1319] 8. After the save operation, the server creates an HTTP response containing the evaluation score on the terminal and sends the evaluation result in JSON format in the response body.

[1320] 9. The device receives the HTTP response and parses the JSON response body using JavaScript. The evaluation result is displayed in a UI component (e.g., the evaluation result section of the dashboard), visually informing the user that "Q1 sales growth rate evaluation: 70 points".

[1321] Examples of prompt statements are as follows:

[1322] "Project B's objective is a 10% cost reduction for the department, and the actual result was a 5% cost reduction in Q1. Please generate an evaluation score based on this objective and actual data."

[1323] As described above, the system of the present invention provides a specific form for automating the evaluation process and improving the objectivity and efficiency of the evaluation.

[1324] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1325] Step 1:

[1326] The user enters the goals and performance data to be evaluated.

[1327] Input: Data entered by the user in the device evaluation form (e.g., "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1")

[1328] Action: The user opens a browser and accesses a specific URL. The user enters goal and performance data into an evaluation form and clicks the "Submit" button.

[1329] Output: The input data is temporarily stored on the terminal.

[1330] Step 2:

[1331] The terminal sends the entered data to the server.

[1332] Input: Data entered in the evaluation form

[1333] Operation: The device uses the browser's JavaScript code to convert the form data into JSON format. The converted data is sent to the server using the HTTPS protocol with SSL / TLS.

[1334] Output: JSON data sent to the server

[1335] Step 3:

[1336] The server receives, verifies, and stores the data.

[1337] Input: JSON data sent from the device

[1338] Operation: The server receives an HTTP request and checks the format of the received data and verifies required fields. Once verification is complete, the data is saved to the database. The data is then inserted into the appropriate table in the database using an SQL INSERT statement.

[1339] Output: Evaluation data stored in the database

[1340] Step 4:

[1341] The server activates a generative AI based on the stored data and begins the analysis process.

[1342] Input: Evaluation data stored in the database

[1343] Operation: The server executes a Python script and loads a machine learning model (e.g., scikit-learn or TensorFlow). It then passes data from a stored database to the model.

[1344] Output: Evaluation data received by the generative AI

[1345] Step 5:

[1346] The generative AI analyzes the data and generates a score based on evaluation criteria.

[1347] Input: Evaluation data passed to the generative AI

[1348] Operation: The generative AI analyzes data based on pre-defined evaluation criteria. For example, it might evaluate "5% cost reduction = 70 points." The score is stored in temporary memory.

[1349] Output: Generated evaluation score

[1350] Step 6:

[1351] The server saves the generated evaluation results.

[1352] Input: Evaluation score generated by a generative AI

[1353] Operation: The server receives the evaluation score and saves it back to the database. It executes an SQL query such as "INSERT INTO scoretable (project, score) VALUES ('project B', 70);".

[1354] Output: Evaluation scores stored in the database

[1355] Step 7:

[1356] The server sends the evaluation results to the terminal.

[1357] Input: Evaluation score stored in the database

[1358] Operation: The server generates an evaluation score as an HTTP response and sends the evaluation result to the terminal in JSON format.

[1359] Output: JSON data of the evaluation results sent to the terminal.

[1360] Step 8:

[1361] The device displays the evaluation results to the user.

[1362] Input: JSON data of evaluation results sent from the server

[1363] Operation: The device receives an HTTP response and parses the JSON response body using JavaScript code. The evaluation result is displayed in a UI component (e.g., the evaluation results section of the dashboard), visually informing the user of "Q1 sales growth rate evaluation: 70 points".

[1364] Output: Evaluation results displayed on the user's screen

[1365] The above describes the specific processing steps in the system of the present invention. This ensures objectivity and efficiency in evaluation, and realizes an accurate and rapid evaluation process.

[1366] (Application Example 1)

[1367] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1368] Traditional personnel evaluation and performance evaluation systems lacked objectivity and efficiency, often involving subjective judgments, leading to unfair evaluation results. Furthermore, the evaluation process was time-consuming and labor-intensive. In addition, performance evaluation in logistics center management was highly subjective, making efficient improvement measures difficult.

[1369] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1370] In this invention, the server includes means for the user to input target and performance data to be evaluated, means for the terminal to transmit the input data to the server, means for the server to receive and store the data, means for the server to activate a generative AI based on the stored data and start an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, means for the server to store the generated evaluation results, means for the terminal to display the evaluation results to the user, and means for logging, and means for generating an evaluation score using a generative AI that calculates performance based on the input data of targets and performance. This improves the objectivity and efficiency of the evaluation, enabling rapid and fair performance evaluation of the logistics center.

[1371] A "user" is the entity that accesses the system and inputs goal and performance data.

[1372] A "terminal" is a computer device used to send data entered by a user to a server.

[1373] A "server" is a computer device that stores data received from terminals, initiates the analysis process, generates evaluation results, and stores them.

[1374] "Generative AI" refers to artificial intelligence models that analyze input data and generate scores based on evaluation criteria.

[1375] "Evaluation criteria" refer to pre-set rules or standards that a generative AI follows when generating a score.

[1376] A "score" is an evaluation value generated by a generative AI based on evaluation criteria.

[1377] A "logging means" is a means that has the function of recording and saving operation logs such as evaluation processes and data reception and storage.

[1378] "Target and performance data" refers to the specific numerical targets and performance data entered by the user for evaluation.

[1379] "Results" refer to data on the actual outcomes achieved in relation to the goals.

[1380] "Data integrity" refers to the state in which received data remains accurate and unchanged from what was intended by the sender.

[1381] "Consistency" refers to a state where received data is consistent with other data and existing systems, and free from contradictions.

[1382] To implement this invention, it is necessary to construct a system in which users, terminals, and servers collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which users input goal and performance data, and a generative AI analyzes this data to generate an evaluation score.

[1383] User-side actions

[1384] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input specific objectives such as "Project A's objective is a 15% increase in sales" or actual performance data such as "Q1 sales increased by 10%."

[1385] Terminal-side operation

[1386] The terminal's role is to send data entered by the user to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP request. Data transmission is protected using security protocols such as SSL / TLS.

[1387] Server-side operation

[1388] The server's role is to receive and store data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server launches a generative AI. This uses a machine learning model implemented in a programming language such as Python.

[1389] The generative AI analyzes the input target and performance data and generates scores based on pre-set evaluation criteria. For example, if the evaluation criteria for sales growth rate are trained to be "10% increase = 85 points," the AI ​​will generate scores accordingly. The server stores the generated scores in a database.

[1390] Displaying Results

[1391] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points" will be displayed.

[1392] A series of specific examples

[1393] For example, the following evaluation process is possible.

[1394] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[1395] 2. The device sends this data to the server.

[1396] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[1397] 4. The server activates the generative AI and analyzes the data.

[1398] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the server saves this evaluation score to the database.

[1399] 6. The server sends the evaluation score to the terminal.

[1400] 7. The device displays the evaluation score to the user.

[1401] Examples of prompts to input into a generative AI model

[1402] "Employee A's Q1 target was a 15% reduction in inventory. Their actual result was a 10% reduction. Please calculate their performance score."

[1403] Hardware and software to be used

[1404] Server: Uses Flask and SQLite for data processing and analysis.

[1405] Generative AI: Python and scikit-learn are used for score calculation.

[1406] Data protection: Uses SSL / TLS protocol.

[1407] Frontend: Utilizes a web interface optimized for smartphones.

[1408] As a result, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[1409] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1410] Step 1: The user enters goal and performance data.

[1411] ---

[1412] Users access the system's evaluation form using their own devices and enter the evaluation target (e.g., "15% increase in sales") and performance data (e.g., "Q1 sales increased by 10%"). The entered data is saved on the device.

[1413] Step 2: The device sends data to the server.

[1414] ---

[1415] The terminal formats the data entered by the user into the appropriate format and sends it to the server using an HTTP request. SSL / TLS protocol is used to protect the data. Input data includes numerical data for targets and actual results. The output is the data sent to the server.

[1416] Step 3: The server receives and stores the data.

[1417] ---

[1418] The server receives data sent from the terminal. It then checks the integrity and validity of the received data. Once the data is deemed acceptable, it saves it to a database (such as SQLite). In this case, the input is the data sent from the terminal, and the output is the data stored in the database.

[1419] Step 4: The server starts the generative AI model and begins the analysis process.

[1420] ---

[1421] The server launches a generative AI model using data stored in the database. This AI model is implemented using Python or scikit-learn. The generative AI analyzes the data based on pre-defined evaluation criteria and generates a score. The input is stored target and performance data, and the output is the generated evaluation score.

[1422] Step 5: The server saves the generated evaluation score.

[1423] ---

[1424] The evaluation score generated by the generative AI is then saved again to the database by the server. The input is the score generated by the generative AI, and the output is the score saved in the database.

[1425] Step 6: The server sends the evaluation results to the terminal.

[1426] ---

[1427] The server sends the generated evaluation score to the terminal. It returns data containing the evaluation score in an HTTP response. The input is the score stored in the database, and the output is the score data sent to the terminal.

[1428] Step 7: The device displays the evaluation results to the user.

[1429] ---

[1430] The terminal displays the evaluation results received from the server on the user's screen. Specifically, evaluation results such as "Q1 Sales Growth Rate Evaluation: 85 points" can be seen through the dashboard function. The input is the score data sent from the server, and the output is the evaluation result displayed on the user's screen.

[1431] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1432] To implement the present invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion engine collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which the user inputs goal and performance data, and the generative AI and emotion engine analyze this data to generate an evaluation score.

[1433] User-side actions

[1434] The user's role is to access the system and input the objectives and performance data to be evaluated. The user uses their own device to access the system's evaluation form and input the relevant data. For example, they might input data such as "Project A's objective is a 15% increase in sales" or "Q1 sales increased by 10%."

[1435] Terminal-side operation

[1436] The terminal's role is to send user-entered data to the server. Once the user has finished entering data into the evaluation form, the terminal formats that data into the appropriate format and sends it to the server using an HTTP POST request. SSL / TLS is used to encrypt the data transmission during this process.

[1437] Server-side operation

[1438] The server is responsible for receiving and storing data sent from the terminal. First, the server checks the completeness and integrity of the received data. Once data verification is complete, it saves it to the database. After saving, the server activates the generative AI and emotion engine. This uses machine learning models and emotion analysis models implemented in programming languages ​​such as Python.

[1439] How generative AI and emotion engines work

[1440] The generative AI analyzes the input goal and performance data and generates a score based on pre-set evaluation criteria. Meanwhile, the emotion engine analyzes the user's facial expressions, voice, and input speed during input to recognize emotional data. This emotional data is incorporated into the evaluation process by the generative AI to generate a more accurate score that takes the user's emotional state into account.

[1441] For example, if the AI ​​is trained with a rating system where "10% increase in sales = 85 points," it will generate a score by incorporating user emotional data. If the emotional data indicates the user's sense of effort or stress level, that information will be reflected in the evaluation.

[1442] Saving and displaying results

[1443] The server stores the generated evaluation results and adjustments based on sentiment data in a database. When saving, it also saves metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data, in addition to the score.

[1444] After the evaluation results are generated and processing is complete, the server sends the evaluation results to the terminal. The terminal receives this data and displays the evaluation results on the user's screen. Specifically, when the user accesses the system's dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points (with sentiment adjustment)" will be displayed.

[1445] Specific example

[1446] For example, the following evaluation process is possible.

[1447] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[1448] 2. The device sends this data to the server.

[1449] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[1450] 4. The server activates the generative AI and emotion engine, and analyzes the data and user emotion data.

[1451] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the emotion engine recognizes "the user's high stress state" and generates a final score of "75 points" as a correction.

[1452] 6. The server saves an evaluation score of 75 points to the database.

[1453] 7. The server sends the evaluation score to the terminal.

[1454] 8. The device displays the evaluation score to the user.

[1455] Through the above process, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, by incorporating an emotion engine, the user's emotional state is reflected in the evaluation, enabling a more comprehensive and human-centered assessment. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[1456] The following describes the processing flow.

[1457] Step 1:

[1458] Users input the target goals and performance data to be evaluated into their terminals. Specifically, users log into the system, access the evaluation form, and input data such as "Project A's goal is a 15% increase in sales" or "Q1 sales increased by 10%."

[1459] Step 2:

[1460] The terminal sends the data entered by the user to the server. After the input is complete, the terminal converts the data to the appropriate format and sends it to the server using an HTTP POST request. At this time, the data is encrypted using SSL / TLS.

[1461] Step 3:

[1462] The server receives data sent from the terminal. The server first checks the completeness and integrity of the received data, and if there are no problems, it saves it to the database. If an error occurs, it returns an error message to the terminal.

[1463] Step 4:

[1464] The server activates the emotion engine. The emotion engine on the server collects data such as the user's facial expressions, voice, and input speed in real time and analyzes the user's emotional state. The analysis results are stored as emotion data.

[1465] Step 5:

[1466] The server launches a generative AI based on the stored data. The server then calls an evaluation machine learning model and starts the evaluation process. Specifically, a model implemented in a programming language such as Python analyzes the target data.

[1467] Step 6:

[1468] Generative AI analyzes data and generates scores based on evaluation criteria. For example, it might generate a score of "85 points" based on an evaluation criterion such as "10% sales growth rate."

[1469] Step 7:

[1470] The server adjusts the score generated based on emotional data. For example, if the user's stress level is high, 5 points are added to the score, and the final score is calculated taking into account the information obtained from the emotional engine.

[1471] Step 8:

[1472] The server saves the generated evaluation results to a database. When saving, in addition to the score, metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data are also saved.

[1473] Step 9:

[1474] The server sends the evaluation results to the terminal. The server returns the evaluation results to the terminal as an HTTP response. The terminal receives this response.

[1475] Step 10:

[1476] The device displays the evaluation results to the user. Specifically, when the user accesses the dashboard, an evaluation result such as "Q1 Sales Growth Rate Evaluation: 85 points (with sentiment adjustment)" is displayed. The user can then use this information to take further action or make decisions.

[1477] Through these steps, users can eliminate subjective judgments and quickly obtain objective and consistent evaluation results. Furthermore, by incorporating an emotion engine, the user's emotional state is reflected in the evaluation, enabling a more comprehensive and human-centered assessment. Because the entire system is automated, the effort and time required for the evaluation process are significantly reduced.

[1478] (Example 2)

[1479] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1480] Modern evaluation systems suffer from problems with subjectivity and efficiency in the evaluation process. Specifically, traditional evaluation systems rely heavily on the subjectivity of evaluators, often lacking consistency and objectivity in their assessments. Furthermore, proper analysis of input data and rapid provision of results require considerable effort and time, making efficient process management difficult. In addition, because they do not consider the user's emotional state, evaluation results do not accurately reflect the user's actual effort or stress level, which is a significant challenge.

[1481] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for verifying the integrity and consistency of the stored data, means for starting a generative AI and an emotion analysis engine and initiating data analysis, and means for generating a score based on evaluation criteria and reflecting the user's emotion data in the evaluation. This enhances the objectivity and consistency of the evaluation and enables a rapid and effective evaluation process. Furthermore, by considering the user's emotional state, a more human-centered and comprehensive evaluation becomes possible.

[1482] A "user" is an individual or organization that accesses the system and enters goal and performance data.

[1483] A "terminal" is a computer device used by a user to input data and send it to a server.

[1484] A "server" is a device that receives and stores data sent from users and terminals, and performs data analysis by activating generative AI and emotion analysis engines.

[1485] "Target data" refers to data that shows the specific goals and objectives that are being evaluated.

[1486] "Performance data" refers to data that shows the actual results and outcomes in relation to the target.

[1487] "Generative AI" refers to machine learning models used to generate evaluation scores based on input goal and performance data.

[1488] An "emotion analysis engine" is a system that analyzes data such as the user's facial expressions, voice, and input speed, and reflects the user's emotional state in its evaluation.

[1489] "Evaluation criteria" refer to pre-set standards or rules that generative AIs use when generating evaluation scores.

[1490] A "score" is a numerical representation of the evaluation result generated by a generative AI based on evaluation criteria.

[1491] "Metadata" refers to additional information such as the date and time the evaluation results were generated, the evaluation criteria, and sentiment data.

[1492] To implement this invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and sentiment analysis engine collaborate to perform the evaluation process. This system improves the objectivity and efficiency of evaluation through a process in which the user inputs goal and performance data, which is then analyzed and an evaluation score is generated.

[1493] User-side actions

[1494] Users access the system and input the goals and performance data to be evaluated. For example, a user might use a web browser to access the system's evaluation form and input data such as "Project A Goal: 15% increase in sales" and "Actual: 10% increase in sales in Q1."

[1495] Terminal-side operation

[1496] The terminal sends the data entered by the user to the server. After the user has finished entering the data, the terminal formats this data into JSON format and sends it to the server using an HTTP POST request. SSL / TLS is used to encrypt the data during this process to ensure security.

[1497] Server-side operation

[1498] The server receives and stores data sent from the terminal. First, the server verifies the integrity and validity of the received data. For example, it checks the hash value of the data to ensure it hasn't been tampered with. Once verification is complete, the server saves the data to the database.

[1499] How generative AI and emotion analysis engines work

[1500] After the data has been saved, the server starts the generative AI and sentiment analysis engine. The generative AI uses a Python machine learning model, and the sentiment analysis engine also utilizes Python libraries. These models are then started, and data analysis begins.

[1501] Generative AI analyzes input data based on pre-trained evaluation criteria and generates an evaluation score. For example, an evaluation criterion such as "10% increase in sales = 85 points" is set. On the other hand, the emotion analysis engine generates emotion data by analyzing the user's facial expressions, voice, input speed, etc. In this invention, a more accurate evaluation score is generated by incorporating the user's emotion data into the evaluation.

[1502] Saving and displaying results

[1503] The server stores the generated evaluation results and related metadata (evaluation date and time, evaluation criteria, sentiment data, etc.) in a database. After recording is complete, the server sends the evaluation results to the terminal. The terminal receives the transmitted evaluation results and displays them on the user's screen. For example, when a user accesses the system's dashboard, the results might be displayed as "Q1 Sales Growth Rate Evaluation: 90 points (with sentiment adjustment)".

[1504] Specific example

[1505] The following is an example of a specific evaluation process.

[1506] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department," and "Actual: 5% cost reduction in Q1."

[1507] 2. The device converts this data to JSON format and sends it to the server.

[1508] 3. The server receives the data, verifies its integrity and consistency, and then stores it in the database.

[1509] 4. The server starts the generative AI and emotion analysis engine and begins data analysis.

[1510] 5. The generative AI evaluates "5% cost reduction = 70 points," and the emotion analysis engine recognizes the user's high-stress state, resulting in a final score of "75 points."

[1511] 6. The server saves the evaluation result of 75 points and related metadata to the database.

[1512] 7. The server sends the evaluation results to the terminal.

[1513] 8. The device displays the evaluation score on the user screen, showing "Q1 Cost Reduction Evaluation: 75 points (with sentiment adjustment)".

[1514] Through this process, users can obtain quick and objective evaluation results. The introduction of an emotion analysis engine enables a comprehensive evaluation that reflects the user's emotional state, significantly reducing effort and time.

[1515] Example of a prompt

[1516] For example, here are some examples of prompt statements to input into a generative AI model:

[1517] "Project A's goal was a 15% increase in sales. Sales increased by 10% in the first quarter. Based on user input speed and facial expressions, it appears the user was under high stress during the evaluation process. Please generate the optimal evaluation score based on this information."

[1518] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1519] Step 1:

[1520] The user enters the goals and performance data to be evaluated.

[1521] Specific operation: The user accesses the system's evaluation form using a web browser and enters data such as "Project A's goal: 15% increase in sales" and "Actual results: 10% increase in sales in Q1".

[1522] Input: Target data and performance data.

[1523] Output: Data entered into the evaluation form.

[1524] Step 2:

[1525] The terminal sends the data entered by the user to the server.

[1526] Specific operation: The terminal formats this data into JSON format and sends it to the server via an HTTP POST request. SSL / TLS is used to encrypt the data during this process.

[1527] Input: Target data and performance data formatted in JSON format.

[1528] Output: Encrypted HTTP POST request.

[1529] Step 3:

[1530] The server receives and stores the data sent from the terminal.

[1531] Specific operation: The server first verifies the integrity and consistency of the received data and checks the data's hash value. Once verification is complete, it saves the data to the database.

[1532] Input: Encrypted data.

[1533] Output: Data stored in the database.

[1534] Step 4:

[1535] The server starts up the generative AI and the emotion analysis engine.

[1536] Specific operation: The server runs a generative AI model and sentiment analysis engine via a Python script.

[1537] Input: Saved data.

[1538] Output: An AI model and sentiment analysis engine ready for analysis.

[1539] Step 5:

[1540] Generative AI analyzes input data based on evaluation criteria and generates an evaluation score.

[1541] Specific operation: The generative AI analyzes the data based on pre-trained evaluation criteria. The rule used as a prompt is "10% increase in sales = 85 points".

[1542] Input: Evaluation criteria and saved data.

[1543] Output: Primary evaluation score.

[1544] Step 6:

[1545] The emotion analysis engine analyzes the user's emotional data.

[1546] Specific operation: The emotion analysis engine generates emotion data from the user's facial expressions, voice, input speed, etc.

[1547] Input: User behavior data.

[1548] Output: Sentiment data.

[1549] Step 7:

[1550] The generative AI and the emotion analysis engine work together to generate the final evaluation score.

[1551] Specific operation: The generative AI calculates the final evaluation score by reflecting the emotional data. For example, it corrects an initial evaluation score of 85 points to 90 points.

[1552] Input: Primary evaluation score and sentiment data.

[1553] Output: Final evaluation score.

[1554] Step 8:

[1555] The server stores the generated evaluation results and associated metadata.

[1556] Specific operation: The server stores evaluation results and related metadata (evaluation date and time, evaluation criteria, sentiment data, etc.) in the database.

[1557] Input: Final rating score and metadata.

[1558] Output: Evaluation results and metadata stored in the database.

[1559] Step 9:

[1560] The server sends the evaluation results to the terminal.

[1561] Specific operation: The server sends the evaluation results to the terminal as an HTTP response.

[1562] Input: Final rating score and metadata.

[1563] Output: The evaluation results that were sent.

[1564] Step 10:

[1565] The device displays the evaluation results on the user's screen.

[1566] Specific operation: The terminal analyzes the submitted evaluation results and displays "Q1 Sales Growth Rate Evaluation: 90 points (with sentiment adjustment)" on the user's screen.

[1567] Input: Evaluation results sent from the server.

[1568] Output: The evaluation results displayed to the user.

[1569] (Application Example 2)

[1570] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1571] In modern performance evaluation systems, objectivity and accuracy are challenges when evaluating users' goals and performance data. Furthermore, traditional systems often fail to reflect users' emotional states in evaluations, resulting in evaluations that tend to be purely numerical. This makes fair evaluation and comprehensive, human-centered assessments difficult.

[1572] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for starting a generative AI and an emotion recognition engine and initiating an analysis process, means for the generative AI to analyze the data and generate a score based on evaluation criteria, and means for the emotion recognition engine to acquire the user's emotion data and reflect it in the evaluation. This makes it possible to perform a more comprehensive and fair evaluation that takes into account the user's emotion data in addition to their goal and performance data.

[1573] A "user" is an individual or organization that inputs the objectives and performance data to be evaluated.

[1574] A "terminal" is a device that sends data entered by the user to a server and receives and displays evaluation results from the server.

[1575] A "server" is a computing system that receives, stores, and analyzes data sent from a terminal.

[1576] "Generative AI" is artificial intelligence that analyzes goal and performance data entered by the user and generates scores based on pre-trained evaluation criteria.

[1577] An "emotion recognition engine" is an analytical engine that acquires user emotion data and incorporates it into evaluations.

[1578] "Data" refers to information about goals and performance entered by the user.

[1579] A "score" is an evaluation value generated by a generative AI as a result of analyzing data based on evaluation criteria.

[1580] "Emotional data" refers to information about a user's emotional state, obtained from their facial expressions, voice, and other sources.

[1581] "Evaluation criteria" are predetermined standards based on how a generative AI generates a score.

[1582] "Integrity" refers to the check items to ensure that the entered data has not been tampered with.

[1583] "Consistency" refers to the check items that verify whether the entered data conforms to the specified format and content.

[1584] To implement this invention, it is necessary to construct a system in which the user, terminal, server, generative AI, and emotion recognition engine collaborate to perform the evaluation process. The detailed operation of this system is described below.

[1585] User-side actions

[1586] Users access the system and input the objectives and performance data to be evaluated. Specifically, users input data such as "Project A's objective is to reduce the product defect rate by 10%" or "Actual: Material defect rate reduced by 6%" into the terminal. After input, the terminal formats the data into the appropriate format and sends it to the server.

[1587] Terminal-side operation

[1588] The terminal's role is to send data entered by the user to the server. This process uses an HTTP POST request and encrypts the data transmission using SSL / TLS. The transmitted data includes the user's goals and performance data.

[1589] Server-side operation

[1590] The server receives data sent from the terminal and first checks its integrity and consistency. This includes verifying that the data has not been tampered with and that it conforms to the correct format. After verification is complete, the data is saved to the database.

[1591] After saving is complete, the server starts the generative AI and emotion recognition engine. This process uses machine learning models (e.g., linear regression models and neural networks) and emotion analysis models implemented in programming languages ​​such as Python. The generative AI analyzes the input data based on pre-trained evaluation criteria and generates a score. Meanwhile, the emotion recognition engine analyzes emotion data obtained from the user's facial expressions and voice and incorporates it into the evaluation.

[1592] Specific operation of the emotion recognition engine

[1593] The emotion recognition engine uses face recognition (face_recognition) and speech recognition (speech_recognition) libraries to analyze the user's facial expressions and voice data. For example, it uses a camera to capture the user's facial expressions as images and recognize their emotions. It also acquires voice data and performs speech recognition to analyze emotions from the user's voice. The analysis results are reflected in a score as an emotional state such as "positive," "neutral," or "negative."

[1594] Saving and displaying results

[1595] The server stores the generated evaluation results and adjustments based on sentiment data in a database. The data stored includes metadata such as the date and time the evaluation was performed, evaluation criteria, and sentiment data, in addition to the score. After processing is complete, the server sends the evaluation results to the terminal, and the terminal displays the evaluation results on the user's screen. Specifically, it will display something like "Evaluation result: 75 points (with sentiment adjustment)."

[1596] Specific example

[1597] For example, the following evaluation process is possible:

[1598] 1. The user enters the following data into the terminal: "Project B Goal: 10% cost reduction for the department" and "Actual: 5% cost reduction in Q1".

[1599] 2. The device sends this data to the server.

[1600] 3. The server receives the data, checks its integrity and consistency, and then stores it in the database.

[1601] 4. The server activates the generative AI and emotion recognition engine, and analyzes the data and user emotion data.

[1602] 5. The AI ​​evaluates "5% cost reduction = 70 points," and the emotion recognition engine recognizes "the user's high stress state" and generates a final score of "75 points" as a correction.

[1603] 6. The server saves an evaluation score of 75 points to the database.

[1604] 7. The server sends the evaluation score to the terminal.

[1605] 8. The device displays the evaluation score to the user.

[1606] Example of a prompt

[1607] The following are examples of prompts to input into a generative AI model:

[1608] The goal of Project A is to reduce the product defect rate by 10%.

[1609] Results: Material defect rate reduced by 6%

[1610] Facial expression analysis result: positive

[1611] Voice analysis results: neutral

[1612] In this way, combining generative AI with an emotion recognition engine can improve the objectivity and accuracy of evaluations of user goal and performance data. Furthermore, by incorporating emotional data, a comprehensive evaluation that reflects the user's emotional state becomes possible.

[1613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1614] Step 1:

[1615] The user inputs the target and performance data to be evaluated into the terminal. Specifically, they enter data such as "Project A's target is a 10% reduction in product defect rate" or "Actual: Material defect rate reduced by 6%" into the designated input fields. This completes the data input process (input: target and performance data, output: formatted data).

[1616] Step 2:

[1617] The terminal sends the goal and performance data entered by the user to the server. The transmission uses an HTTP POST request and SSL / TLS to encrypt the data (input: formatted data, output: data sent to the server).

[1618] Step 3:

[1619] The server receives data sent from the terminal and checks its integrity and consistency. This includes checking for data tampering and verifying format compliance. Once verification is complete, the data is stored in the database (input: sent data, output: verified data).

[1620] Step 4:

[1621] The server activates the generative AI and emotion recognition engine based on the stored data. First, the generative AI analyzes the input data and generates a score based on pre-trained evaluation criteria (input: stored data, output: initial evaluation score).

[1622] Step 5:

[1623] The emotion recognition engine acquires and analyzes the user's emotional data. This process involves using the face recognition library (face_recognition) to acquire facial expression data and the speech recognition library (speech_recognition) to analyze speech data. The analysis results are obtained as emotional states such as "positive," "neutral," and "negative" (input: image and audio data, output: emotional data).

[1624] Step 6:

[1625] The server adjusts the generative AI's score based on the analyzed emotional data. For example, if the generative AI evaluates "5% cost reduction = 70 points" and the emotional recognition engine recognizes "the user is in a high-stress state," it will generate a final score of "75 points" as a correction (input: initial evaluation score, emotional data; output: corrected final score).

[1626] Step 7:

[1627] The server stores the generated evaluation results and adjustments based on sentiment data in a database. The data stored includes metadata such as the evaluation date and time, evaluation criteria, and sentiment data, in addition to the score (input: final evaluation score, output: stored evaluation data).

[1628] Step 8:

[1629] The server sends the evaluation results to the terminal, and the terminal displays the evaluation results to the user. Specifically, it will display something like "Evaluation result: 75 points (with sentiment adjustment)" (Input: saved evaluation data, Output: user's display screen).

[1630] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1631] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1632] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1633] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1634] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1635] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1636] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1637] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1638] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1639] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1640] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1641] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1642] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1643] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1644] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1645] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1646] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1647] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1648] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1649] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1650] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1651] The following is further disclosed regarding the embodiments described above.

[1652] (Claim 1)

[1653] A means for users to input the goals and performance data to be evaluated,

[1654] A means for the terminal to send the entered data to the server,

[1655] The means by which the server receives and stores data,

[1656] A means by which the server activates a generative AI based on the stored data and starts the analysis process,

[1657] A means by which a generative AI analyzes data and generates a score based on evaluation criteria,

[1658] A means for saving the evaluation results generated by the server,

[1659] A means by which the terminal displays the evaluation results to the user,

[1660] A system that includes this.

[1661] (Claim 2)

[1662] The system according to claim 1, wherein the generative AI model that generates a score based on evaluation criteria is pre-trained.

[1663] (Claim 3)

[1664] The system according to claim 1, wherein the server that receives data entered by a user includes means for checking the integrity and validity of the data.

[1665] "Example 1"

[1666] (Claim 1)

[1667] A means for users to input the goals and performance data to be evaluated,

[1668] A means for the terminal to send the entered data to the server,

[1669] The server has a means of receiving, verifying, and storing data,

[1670] A means by which the server activates a generative AI based on the stored data and starts the analysis process,

[1671] A means by which a generative AI analyzes data and generates a score based on evaluation criteria,

[1672] A means for saving the evaluation results generated by the server,

[1673] A means for the server to send evaluation results to the terminal,

[1674] A means by which the terminal displays the evaluation results to the user,

[1675] A system that includes this.

[1676] (Claim 2)

[1677] The system according to claim 1, wherein the generative AI model that generates a score based on evaluation criteria is pre-trained.

[1678] (Claim 3)

[1679] The system according to claim 1, wherein the server that receives and verifies data entered by a user includes means for checking the integrity and validity of the data.

[1680] "Application Example 1"

[1681] (Claim 1)

[1682] A means for users to input the goals and performance data to be evaluated,

[1683] A means for the terminal to send the entered data to the server,

[1684] The means by which the server receives and stores data,

[1685] A means by which the server activates a generative AI based on the stored data and starts the analysis process,

[1686] A means by which a generative AI analyzes data and generates a score based on evaluation criteria,

[1687] A means for the server to store the generated evaluation results,

[1688] A means by which the terminal displays the evaluation results to the user,

[1689] A server including logging means,

[1690] A means for generating an evaluation score using a generative AI that calculates performance based on input data of goals and achievements,

[1691] A system that includes this.

[1692] (Claim 2)

[1693] The system according to claim 1, wherein the generative AI model that generates a score based on evaluation criteria is pre-trained.

[1694] (Claim 3)

[1695] The system according to claim 1, wherein the server that receives data entered by a user includes means for checking the integrity and validity of the data.

[1696] "Example 2 of combining an emotion engine"

[1697] (Claim 1)

[1698] A means for users to input the goals and performance data to be evaluated,

[1699] A means for the terminal to send the entered data to the server,

[1700] The means by which the server receives and stores data,

[1701] A means for verifying the integrity and reliability of data stored on the server,

[1702] The server starts up a generative AI and an emotion analysis engine, and begins data analysis.

[1703] A generative AI generates scores based on evaluation criteria, and an emotion analysis engine incorporates user emotion data into the evaluation.

[1704] A server provides means for storing the generated evaluation results and related metadata,

[1705] A means by which the terminal displays the evaluation results to the user,

[1706] A system that includes this.

[1707] (Claim 2)

[1708] The system according to claim 1, wherein the generative AI model that generates a score based on evaluation criteria is pre-trained.

[1709] (Claim 3)

[1710] The system according to claim 1, comprising a means for generating emotional data by analyzing the user's facial expressions, voice, input speed, etc., using an emotion analysis engine.

[1711] "Application example 2 when combining with an emotional engine"

[1712] (Claim 1)

[1713] A means for users to input the goals and performance data to be evaluated,

[1714] A means for the terminal to send the entered data to the server,

[1715] The means by which the server receives and stores data,

[1716] A means by which the server activates a generative AI and an emotion recognition engine based on the stored data and starts the analysis process,

[1717] A means by which a generative AI analyzes data and generates a score based on evaluation criteria,

[1718] A means by which the emotion recognition engine acquires user emotion data and reflects it in the evaluation,

[1719] A server provides means for storing the generated evaluation results and corrections based on sentiment data,

[1720] A means by which the terminal displays the evaluation results to the user,

[1721] A system that includes this.

[1722] (Claim 2)

[1723] The system according to claim 1, wherein the generative AI model that generates a score based on evaluation criteria is pre-trained.

[1724] (Claim 3)

[1725] The system according to claim 1, wherein the server that receives data entered by a user includes means for checking the integrity and validity of the data. [Explanation of Symbols]

[1726] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to input the goals and performance data to be evaluated, A means for the terminal to send the entered data to the server, The means by which the server receives and stores data, A means by which the server activates a generative AI based on the stored data and starts the analysis process, A means by which a generative AI analyzes data and generates a score based on evaluation criteria, A means for the server to store the generated evaluation results, A means by which the terminal displays the evaluation results to the user, A system that includes this.

2. The system according to claim 1, wherein the generative AI model that generates a score based on evaluation criteria is pre-trained.

3. The system according to claim 1, wherein the server that receives data entered by a user includes means for checking the integrity and validity of the data.

Images